Shao-Bo Lin

Shao-Bo Lin, Di Wang, Ding-Xuan Zhou

This paper proposes a sketching strategy based on spherical designs, which is applied to the classical spherical basis function approach for massive spherical data fitting. We conduct theoretical analysis and numerical verifications to demonstrate the feasibility of the proposed { sketching} strategy. From the theoretical side, we prove that sketching based on spherical designs can reduce the computational burden of the spherical basis function approach without sacrificing its approximation capability. In particular, we provide upper and lower bounds for the proposed { sketching} strategy to fit noisy data on spheres. From the experimental side, we numerically illustrate the feasibility of the sketching strategy by showing its comparable fitting performance with the spherical basis function approach. These interesting findings show that the proposed sketching strategy is capable of fitting massive and noisy data on spheres.

Di Wang, Yao Wang, Shao-Bo Lin

In recent years, large amounts of electronic health records (EHRs) concerning chronic diseases have been collected to facilitate medical diagnosis. Modeling the dynamic properties of EHRs related to chronic diseases can be efficiently done using dynamic treatment regimes (DTRs). While reinforcement learning (RL) is a widely used method for creating DTRs, there is ongoing research in developing RL algorithms that can effectively handle large amounts of data. In this paper, we present a scalable kernel-based distributed Q-learning algorithm for generating DTRs. We perform both theoretical assessments and numerical analysis for the proposed approach. The results demonstrate that our algorithm significantly reduces the computational complexity associated with the state-of-the-art deep reinforcement learning methods, while maintaining comparable generalization performance in terms of accumulated rewards across stages, such as survival time or cumulative survival probability.

Zhi Han, Baichen Liu, Shao-Bo Lin et al.

This paper studies the performance of deep convolutional neural networks (DCNNs) with zero-padding in feature extraction and learning. After verifying the roles of zero-padding in enabling translation-equivalence, and pooling in its translation-invariance driven nature, we show that with similar number of free parameters, any deep fully connected networks (DFCNs) can be represented by DCNNs with zero-padding. This demonstrates that DCNNs with zero-padding is essentially better than DFCNs in feature extraction. Consequently, we derive universal consistency of DCNNs with zero-padding and show its translation-invariance in the learning process. All our theoretical results are verified by numerical experiments including both toy simulations and real-data running.

Di Wang, Xiaotong Liu, Shao-Bo Lin et al.

Data silos, mainly caused by privacy and interoperability, significantly constrain collaborations among different organizations with similar data for the same purpose. Distributed learning based on divide-and-conquer provides a promising way to settle the data silos, but it suffers from several challenges, including autonomy, privacy guarantees, and the necessity of collaborations. This paper focuses on developing an adaptive distributed kernel ridge regression (AdaDKRR) by taking autonomy in parameter selection, privacy in communicating non-sensitive information, and the necessity of collaborations in performance improvement into account. We provide both solid theoretical verification and comprehensive experiments for AdaDKRR to demonstrate its feasibility and effectiveness. Theoretically, we prove that under some mild conditions, AdaDKRR performs similarly to running the optimal learning algorithms on the whole data, verifying the necessity of collaborations and showing that no other distributed learning scheme can essentially beat AdaDKRR under the same conditions. Numerically, we test AdaDKRR on both toy simulations and two real-world applications to show that AdaDKRR is superior to other existing distributed learning schemes. All these results show that AdaDKRR is a feasible scheme to defend against data silos, which are highly desired in numerous application regions such as intelligent decision-making, pricing forecasting, and performance prediction for products.

Shao-Bo Lin

This paper focuses on approximation and learning performance analysis for deep convolutional neural networks with zero-padding and max-pooling. We prove that, to approximate $r$-smooth function, the approximation rates of deep convolutional neural networks with depth $L$ are of order $ (L^2/\log L)^{-2r/d} $, which is optimal up to a logarithmic factor. Furthermore, we deduce almost optimal learning rates for implementing empirical risk minimization over deep convolutional neural networks.

Shao-Bo Lin, Tao Li, Shaojie Tang et al.

With the help of massive data and rich computational resources, deep Q-learning has been widely used in operations research and management science and has contributed to great success in numerous applications, including recommender systems, supply chains, games, and robotic manipulation. However, the success of deep Q-learning lacks solid theoretical verification and interpretability. The aim of this paper is to theoretically verify the power of depth in deep Q-learning. Within the framework of statistical learning theory, we rigorously prove that deep Q-learning outperforms its traditional version by demonstrating its good generalization error bound. Our results reveal that the main reason for the success of deep Q-learning is the excellent performance of deep neural networks (deep nets) in capturing the special properties of rewards namely, spatial sparseness and piecewise constancy, rather than their large capacities. In this paper, we make fundamental contributions to the field of reinforcement learning by answering to the following three questions: Why does deep Q-learning perform so well? When does deep Q-learning perform better than traditional Q-learning? How many samples are required to achieve a specific prediction accuracy for deep Q-learning? Our theoretical assertions are verified by applying deep Q-learning in the well-known beer game in supply chain management and a simulated recommender system.

Di Wang, Shao-Bo Lin, Deyu Meng et al.

Deep learning has made profound impacts in the domains of data mining and AI, distinguished by the groundbreaking achievements in numerous real-world applications and the innovative algorithm design philosophy. However, it suffers from the inconsistency issue between optimization and generalization, as achieving good generalization, guided by the bias-variance trade-off principle, favors under-parameterized networks, whereas ensuring effective convergence of gradient-based algorithms demands over-parameterized networks. To address this issue, we develop a novel sketching scheme based on deep net components for various tasks. Specifically, we use deep net components with specific efficacy to build a sketching basis that embodies the advantages of deep networks. Subsequently, we transform deep net training into a linear empirical risk minimization problem based on the constructed basis, successfully avoiding the complicated convergence analysis of iterative algorithms. The efficacy of the proposed component-based sketching is validated through both theoretical analysis and numerical experiments. Theoretically, we show that the proposed component-based sketching provides almost optimal rates in approximating saturated functions for shallow nets and also achieves almost optimal generalization error bounds. Numerically, we demonstrate that, compared with the existing gradient-based training methods, component-based sketching possesses superior generalization performance with reduced training costs.

Shao-Bo Lin

Parameter selection without communicating local data is quite challenging in distributed learning, exhibing an inconsistency between theoretical analysis and practical application of it in tackling distributively stored data. Motivated by the recently developed Lepskii principle and non-privacy communication protocol for kernel learning, we propose a Lepskii principle to equip distributed kernel ridge regression (DKRR) and consequently develop an adaptive DKRR with Lepskii principle (Lep-AdaDKRR for short) by using a double weighted averaging synthesization scheme. We deduce optimal learning rates for Lep-AdaDKRR and theoretically show that Lep-AdaDKRR succeeds in adapting to the regularity of regression functions, effective dimension decaying rate of kernels and different metrics of generalization, which fills the gap of the mentioned inconsistency between theory and application.

Shao-Bo Lin

This paper focuses on scattered data fitting problems on spheres. We study the approximation performance of a class of weighted spectral filter algorithms, including Tikhonov regularization, Landaweber iteration, spectral cut-off, and iterated Tikhonov, in fitting noisy data with possibly unbounded random noise. For the analysis, we develop an integral operator approach that can be regarded as an extension of the widely used sampling inequality approach and norming set method in the community of scattered data fitting. After providing an equivalence between the operator differences and quadrature rules, we succeed in deriving optimal Sobolev-type error estimates of weighted spectral filter algorithms. Our derived error estimates do not suffer from the saturation phenomenon for Tikhonov regularization in the literature, native-space-barrier for existing error analysis and adapts to different embedding spaces. We also propose a divide-and-conquer scheme to equip weighted spectral filter algorithms to reduce their computational burden and present the optimal approximation error bounds.

Xiaotong Liu, Jinxin Wang, Di Wang et al.

Spherical radial-basis-based kernel interpolation abounds in image sciences including geophysical image reconstruction, climate trends description and image rendering due to its excellent spatial localization property and perfect approximation performance. However, in dealing with noisy data, kernel interpolation frequently behaves not so well due to the large condition number of the kernel matrix and instability of the interpolation process. In this paper, we introduce a weighted spectral filter approach to reduce the condition number of the kernel matrix and then stabilize kernel interpolation. The main building blocks of the proposed method are the well developed spherical positive quadrature rules and high-pass spectral filters. Using a recently developed integral operator approach for spherical data analysis, we theoretically demonstrate that the proposed weighted spectral filter approach succeeds in breaking through the bottleneck of kernel interpolation, especially in fitting noisy data. We provide optimal approximation rates of the new method to show that our approach does not compromise the predicting accuracy. Furthermore, we conduct both toy simulations and two real-world data experiments with synthetically added noise in geophysical image reconstruction and climate image processing to verify our theoretical assertions and show the feasibility of the weighted spectral filter approach.

Shao-Bo Lin

This paper focuses on parameter selection issues of kernel ridge regression (KRR). Due to special spectral properties of KRR, we find that delicate subdivision of the parameter interval shrinks the difference between two successive KRR estimates. Based on this observation, we develop an early-stopping type parameter selection strategy for KRR according to the so-called Lepskii-type principle. Theoretical verifications are presented in the framework of learning theory to show that KRR equipped with the proposed parameter selection strategy succeeds in achieving optimal learning rates and adapts to different norms, providing a new record of parameter selection for kernel methods.

Han Feng, Shao-Bo Lin, Ding-Xuan Zhou

This paper proposes a distributed weighted regularized least squares algorithm (DWRLS) based on spherical radial basis functions and spherical quadrature rules to tackle spherical data that are stored across numerous local servers and cannot be shared with each other. Via developing a novel integral operator approach, we succeed in deriving optimal approximation rates for DWRLS and theoretically demonstrate that DWRLS performs similarly as running a weighted regularized least squares algorithm with the whole data on a large enough machine. This interesting finding implies that distributed learning is capable of sufficiently exploiting potential values of distributively stored spherical data, even though every local server cannot access all the data.

Shao-Bo Lin, Yao Wang, Ding-Xuan Zhou

In this paper, we study the generalization performance of global minima for implementing empirical risk minimization (ERM) on over-parameterized deep ReLU nets. Using a novel deepening scheme for deep ReLU nets, we rigorously prove that there exist perfect global minima achieving almost optimal generalization error bounds for numerous types of data under mild conditions. Since over-parameterization is crucial to guarantee that the global minima of ERM on deep ReLU nets can be realized by the widely used stochastic gradient descent (SGD) algorithm, our results indeed fill a gap between optimization and generalization.

Zirui Sun, Mingwei Dai, Yao Wang et al.

This paper focuses on learning rate analysis of Nyström regularization with sequential sub-sampling for $τ$-mixing time series. Using a recently developed Banach-valued Bernstein inequality for $τ$-mixing sequences and an integral operator approach based on second-order decomposition, we succeed in deriving almost optimal learning rates of Nyström regularization with sequential sub-sampling for $τ$-mixing time series. A series of numerical experiments are carried out to verify our theoretical results, showing the excellent learning performance of Nyström regularization with sequential sub-sampling in learning massive time series data. All these results extend the applicable range of Nyström regularization from i.i.d. samples to non-i.i.d. sequences.

Shao-Bo Lin, Kaidong Wang, Yao Wang et al.

Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind. In particular, the universal consistency of DCNNs remains open. In this paper, we prove that implementing empirical risk minimization on DCNNs with expansive convolution (with zero-padding) is strongly universally consistent. Motivated by the universal consistency, we conduct a series of experiments to show that without any fully connected layers, DCNNs with expansive convolution perform not worse than the widely used deep neural networks with hybrid structure containing contracting (without zero-padding) convolution layers and several fully connected layers.

Yao Wang, Xin Guo, Shao-Bo Lin

Developing efficient kernel methods for regression is very popular in the past decade. In this paper, utilizing boosting on kernel-based weaker learners, we propose a novel kernel-based learning algorithm called kernel-based re-scaled boosting with truncation, dubbed as KReBooT. The proposed KReBooT benefits in controlling the structure of estimators and producing sparse estimate, and is near overfitting resistant. We conduct both theoretical analysis and numerical simulations to illustrate the power of KReBooT. Theoretically, we prove that KReBooT can achieve the almost optimal numerical convergence rate for nonlinear approximation. Furthermore, using the recently developed integral operator approach and a variant of Talagrand's concentration inequality, we provide fast learning rates for KReBooT, which is a new record of boosting-type algorithms. Numerically, we carry out a series of simulations to show the promising performance of KReBooT in terms of its good generalization, near over-fitting resistance and structure constraints.

Shao-Bo Lin, Xiangyu Chang, Xingping Sun

Data sites selected from modeling high-dimensional problems often appear scattered in non-paternalistic ways. Except for sporadic clustering at some spots, they become relatively far apart as the dimension of the ambient space grows. These features defy any theoretical treatment that requires local or global quasi-uniformity of distribution of data sites. Incorporating a recently-developed application of integral operator theory in machine learning, we propose and study in the current article a new framework to analyze kernel interpolation of high dimensional data, which features bounding stochastic approximation error by the spectrum of the underlying kernel matrix. Both theoretical analysis and numerical simulations show that spectra of kernel matrices are reliable and stable barometers for gauging the performance of kernel-interpolation methods for high dimensional data.

Zhi Han, Siquan Yu, Shao-Bo Lin et al.

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantage of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machine learning and pattern recognition. One of the most important challenge of deep learning is to figure out relations between a feature and the depth of deep neural networks (deep nets for short) to reflect the necessity of depth. Our purpose is to quantify this feature-depth correspondence in feature extraction and generalization. We present the adaptivity of features to depths and vice-verse via showing a depth-parameter trade-off in extracting both single feature and composite features. Based on these results, we prove that implementing the classical empirical risk minimization on deep nets can achieve the optimal generalization performance for numerous learning tasks. Our theoretical results are verified by a series of numerical experiments including toy simulations and a real application of earthquake seismic intensity prediction.

Jinshan Zeng, Min Zhang, Shao-Bo Lin

Boosting is a well-known method for improving the accuracy of weak learners in machine learning. However, its theoretical generalization guarantee is missing in literature. In this paper, we propose an efficient boosting method with theoretical generalization guarantees for binary classification. Three key ingredients of the proposed boosting method are: a) the \textit{fully-corrective greedy} (FCG) update in the boosting procedure, b) a differentiable \textit{squared hinge} (also called \textit{truncated quadratic}) function as the loss function, and c) an efficient alternating direction method of multipliers (ADMM) algorithm for the associated FCG optimization. The used squared hinge loss not only inherits the robustness of the well-known hinge loss for classification with outliers, but also brings some benefits for computational implementation and theoretical justification. Under some sparseness assumption, we derive a fast learning rate of the order ${\cal O}((m/\log m)^{-1/4})$ for the proposed boosting method, which can be further improved to ${\cal O}((m/\log m)^{-1/2})$ if certain additional noise assumption is imposed, where $m$ is the size of sample set. Both derived learning rates are the best ones among the existing generalization results of boosting-type methods for classification. Moreover, an efficient early stopping scheme is provided for the proposed method. A series of toy simulations and real data experiments are conducted to verify the developed theories and demonstrate the effectiveness of the proposed method.

Shao-Bo Lin, Di Wang, Ding-Xuan Zhou

This paper focuses on generalization performance analysis for distributed algorithms in the framework of learning theory. Taking distributed kernel ridge regression (DKRR) for example, we succeed in deriving its optimal learning rates in expectation and providing theoretically optimal ranges of the number of local processors. Due to the gap between theory and experiments, we also deduce optimal learning rates for DKRR in probability to essentially reflect the generalization performance and limitations of DKRR. Furthermore, we propose a communication strategy to improve the learning performance of DKRR and demonstrate the power of communications in DKRR via both theoretical assessments and numerical experiments.

Zirui Sun, Shao-Bo Lin

This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridge regression. As a byproduct, we also deduce a sufficient condition for the mixing property to guarantee the optimal learning rates for kernel ridge regression. Our results extend the applicable range of distributed learning from i.i.d. samples to non-i.i.d. sequences.

Xiangyu Chang, Shao-Bo Lin

In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms. We introduce the empirical effective dimension to quantify the increments of iterations in KGD and derive an implementable early stopping strategy. We analyze the performance of the adaptive stopping rule in the framework of learning theory. Using the recently developed integral operator approach, we rigorously prove the optimality of the adaptive stopping rule in terms of showing the optimal learning rates for KGD equipped with this rule. Furthermore, a sharp bound on the number of iterations in KGD equipped with the proposed early stopping rule is also given to demonstrate its computational advantage.

Charles K. Chui, Shao-Bo Lin, Bo Zhang et al.

The great success of deep learning poses urgent challenges for understanding its working mechanism and rationality. The depth, structure, and massive size of the data are recognized to be three key ingredients for deep learning. Most of the recent theoretical studies for deep learning focus on the necessity and advantages of depth and structures of neural networks. In this paper, we aim at rigorous verification of the importance of massive data in embodying the out-performance of deep learning. To approximate and learn spatially sparse and smooth functions, we establish a novel sampling theorem in learning theory to show the necessity of massive data. We then prove that implementing the classical empirical risk minimization on some deep nets facilitates in realization of the optimal learning rates derived in the sampling theorem. This perhaps explains why deep learning performs so well in the era of big data.

Jinshan Zeng, Minrun Wu, Shao-Bo Lin et al.

In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and interpretability. In this paper, we develop a novel efficient classification algorithm, called fast polynomial kernel classification (FPC), to conquer the scalability and storage challenges. Our main tools are a suitable selected feature mapping based on polynomial kernels and an alternating direction method of multipliers (ADMM) algorithm for a related non-smooth convex optimization problem. Fast learning rates as well as feasibility verifications including the efficiency of an ADMM solver with convergence guarantees and the selection of center points are established to justify theoretical behaviors of FPC. Our theoretical assertions are verified by a series of simulations and real data applications. Numerical results demonstrate that FPC significantly reduces the computational burden and storage memory of existing learning schemes such as support vector machines, Nyström and random feature methods, without sacrificing their generalization abilities much.

Shao-Bo Lin, Yu Guang Wang, Ding-Xuan Zhou

Problems in astrophysics, space weather research and geophysics usually need to analyze noisy big data on the sphere. This paper develops distributed filtered hyperinterpolation for noisy data on the sphere, which assigns the data fitting task to multiple servers to find a good approximation of the mapping of input and output data. For each server, the approximation is a filtered hyperinterpolation on the sphere by a small proportion of quadrature nodes. The distributed strategy allows parallel computing for data processing and model selection and thus reduces computational cost for each server while preserves the approximation capability compared to the filtered hyperinterpolation. We prove quantitative relation between the approximation capability of distributed filtered hyperinterpolation and the numbers of input data and servers. Numerical examples show the efficiency and accuracy of the proposed method.

Charles K. Chui, Shao-Bo Lin, Ding-Xuan Zhou

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal function approximation in an arbitrarily high dimensional Euclidian space. It is shown that deep nets have much better performance than shallow nets (with only one hidden layer) in terms of approximation accuracy and learning capabilities. In particular, for learning radial functions, it is shown that near-optimal rate can be achieved by deep nets but not by shallow nets. Our results illustrate the necessity of depth in neural network design for realization of rotation-invariance target functions.

Jinshan Zeng, Shao-Bo Lin, Yuan Yao et al.

In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADMM pair}), mainly motivated by the gradient-free nature of ADMM in avoiding the saturation of sigmoid-type activations and the advantages of deep neural networks with sigmoid-type activations (called deep sigmoid nets) over their rectified linear unit (ReLU) counterparts (called deep ReLU nets) in terms of approximation. In particular, we prove that the approximation capability of deep sigmoid nets is not worse than that of deep ReLU nets by showing that ReLU activation function can be well approximated by deep sigmoid nets with two hidden layers and finitely many free parameters but not vice-verse. We also establish the global convergence of the proposed ADMM for the nonlinearly constrained formulation of the deep sigmoid nets training from arbitrary initial points to a Karush-Kuhn-Tucker (KKT) point at a rate of order ${\cal O}(1/k)$. Besides sigmoid activation, such a convergence theorem holds for a general class of smooth activations. Compared with the widely used stochastic gradient descent (SGD) algorithm for the deep ReLU nets training (called ReLU-SGD pair), the proposed sigmoid-ADMM pair is practically stable with respect to the algorithmic hyperparameters including the learning rate, initial schemes and the pro-processing of the input data. Moreover, we find that to approximate and learn simple but important functions the proposed sigmoid-ADMM pair numerically outperforms the ReLU-SGD pair.

Zheng-Chu Guo, Lei Shi, Shao-Bo Lin

This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additional capacity costs. This verifies the advantage of deep nets in realizing complex features. On the other hand, to realize some simple data feature like the smoothness, we prove that, up to a logarithmic factor, the approximation rate of deep nets is asymptotically identical to that of shallow nets, provided that the depth is fixed. This exhibits a limitation of deep nets in realizing simple features.

Jian Fang, Shaobo Lin, Zongben Xu

Supervised learning frequently boils down to determining hidden and bright parameters in a parameterized hypothesis space based on finite input-output samples. The hidden parameters determine the attributions of hidden predictors or the nonlinear mechanism of an estimator, while the bright parameters characterize how hidden predictors are linearly combined or the linear mechanism. In traditional learning paradigm, hidden and bright parameters are not distinguished and trained simultaneously in one learning process. Such an one-stage learning (OSL) brings a benefit of theoretical analysis but suffers from the high computational burden. To overcome this difficulty, a two-stage learning (TSL) scheme, featured by learning through deterministic assignment of hidden parameters (LtDaHP) was proposed, which suggests to deterministically generate the hidden parameters by using minimal Riesz energy points on a sphere and equally spaced points in an interval. We theoretically show that with such deterministic assignment of hidden parameters, LtDaHP with a neural network realization almost shares the same generalization performance with that of OSL. We also present a series of simulations and application examples to support the outperformance of LtDaHP

Shao-Bo Lin

Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning. The expressivity focuses on finding functions expressible by deep nets but cannot be approximated by shallow nets with the similar number of neurons. It usually implies the large capacity. The generalization aims at deriving fast learning rate for deep nets. It usually requires small capacity to reduce the variance. Different from previous studies on deep learning, pursuing either expressivity or generalization, we take both factors into account to explore the theoretical advantages of deep nets. For this purpose, we construct a deep net with two hidden layers possessing excellent expressivity in terms of localized and sparse approximation. Then, utilizing the well known covering number to measure the capacity, we find that deep nets possess excellent expressive power (measured by localized and sparse approximation) without enlarging the capacity of shallow nets. As a consequence, we derive near optimal learning rates for implementing empirical risk minimization (ERM) on the constructed deep nets. These results theoretically exhibit the advantage of deep nets from learning theory viewpoints.

Charles K. Chui, Shao-Bo Lin, Ding-Xuan Zhou

The subject of deep learning has recently attracted users of machine learning from various disciplines, including: medical diagnosis and bioinformatics, financial market analysis and online advertisement, speech and handwriting recognition, computer vision and natural language processing, time series forecasting, and search engines. However, theoretical development of deep learning is still at its infancy. The objective of this paper is to introduce a deep neural network (also called deep-net) approach to localized manifold learning, with each hidden layer endowed with a specific learning task. For the purpose of illustrations, we only focus on deep-nets with three hidden layers, with the first layer for dimensionality reduction, the second layer for bias reduction, and the third layer for variance reduction. A feedback component also designed to eliminate outliers. The main theoretical result in this paper is the order $\mathcal O\left(m^{-2s/(2s+d)}\right)$ of approximation of the regression function with regularity $s$, in terms of the number $m$ of sample points, where the (unknown) manifold dimension $d$ replaces the dimension $D$ of the sampling (Euclidean) space for shallow nets.

Shao-Bo Lin, Jinshan Zeng, Xiangyu Chang

This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, provided the regression function is smooth. Our second result shows that, for a large number of loss functions, under some Tsybakov noise assumption, if the regression function is infinitely smooth, then SVM with Gaussian kernel can achieve the learning rate of order $m^{-1}$, where $m$ is the number of samples.

Shao-Bo Lin, Xin Guo, Ding-Xuan Zhou

We study distributed learning with the least squares regularization scheme in a reproducing kernel Hilbert space (RKHS). By a divide-and-conquer approach, the algorithm partitions a data set into disjoint data subsets, applies the least squares regularization scheme to each data subset to produce an output function, and then takes an average of the individual output functions as a final global estimator or predictor. We show with error bounds in expectation in both the $L^2$-metric and RKHS-metric that the global output function of this distributed learning is a good approximation to the algorithm processing the whole data in one single machine. Our error bounds are sharp and stated in a general setting without any eigenfunction assumption. The analysis is achieved by a novel second order decomposition of operator differences in our integral operator approach. Even for the classical least squares regularization scheme in the RKHS associated with a general kernel, we give the best learning rate in the literature.

Shaobo Lin, Jinshan Zeng, Xiaoqin Zhang

In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of "constructive neural networks" in approximation theory, we focus on "constructing" rather than "training" feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive feed-forward neural network (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for FNN approximation, but also reaches the optimal learning rate when the regression function is smooth, while the state-of-the-art learning rates established for traditional FNNs are only near optimal (up to a logarithmic factor). A series of numerical simulations are provided to show the efficiency and feasibility of CFN via comparing with the well-known regularized least squares (RLS) with Gaussian kernel and extreme learning machine (ELM).

Lin Xu, Shaobo Lin, Jinshan Zeng et al.

Orthogonal greedy learning (OGL) is a stepwise learning scheme that starts with selecting a new atom from a specified dictionary via the steepest gradient descent (SGD) and then builds the estimator through orthogonal projection. In this paper, we find that SGD is not the unique greedy criterion and introduce a new greedy criterion, called "$δ$-greedy threshold" for learning. Based on the new greedy criterion, we derive an adaptive termination rule for OGL. Our theoretical study shows that the new learning scheme can achieve the existing (almost) optimal learning rate of OGL. Plenty of numerical experiments are provided to support that the new scheme can achieve almost optimal generalization performance, while requiring less computation than OGL.

Xiangyu Chang, Shaobo Lin, Yao Wang

The divide and conquer strategy, which breaks a massive data set into a se- ries of manageable data blocks, and then combines the independent results of data blocks to obtain a final decision, has been recognized as a state-of-the-art method to overcome challenges of massive data analysis. In this paper, we merge the divide and conquer strategy with local average regression methods to infer the regressive relationship of input-output pairs from a massive data set. After theoretically analyzing the pros and cons, we find that although the divide and conquer local average regression can reach the optimal learning rate, the restric- tion to the number of data blocks is a bit strong, which makes it only feasible for small number of data blocks. We then propose two variants to lessen (or remove) this restriction. Our results show that these variants can achieve the optimal learning rate with much milder restriction (or without such restriction). Extensive experimental studies are carried out to verify our theoretical assertions.

Lin Xu, Shaobo Lin, Yao Wang et al.

Re-scale boosting (RBoosting) is a variant of boosting which can essentially improve the generalization performance of boosting learning. The key feature of RBoosting lies in introducing a shrinkage degree to re-scale the ensemble estimate in each gradient-descent step. Thus, the shrinkage degree determines the performance of RBoosting. The aim of this paper is to develop a concrete analysis concerning how to determine the shrinkage degree in $L_2$-RBoosting. We propose two feasible ways to select the shrinkage degree. The first one is to parameterize the shrinkage degree and the other one is to develope a data-driven approach of it. After rigorously analyzing the importance of the shrinkage degree in $L_2$-RBoosting learning, we compare the pros and cons of the proposed methods. We find that although these approaches can reach the same learning rates, the structure of the final estimate of the parameterized approach is better, which sometimes yields a better generalization capability when the number of sample is finite. With this, we recommend to parameterize the shrinkage degree of $L_2$-RBoosting. To this end, we present an adaptive parameter-selection strategy for shrinkage degree and verify its feasibility through both theoretical analysis and numerical verification. The obtained results enhance the understanding of RBoosting and further give guidance on how to use $L_2$-RBoosting for regression tasks.

Shaobo Lin, Yao Wang, Lin Xu

Boosting is a learning scheme that combines weak prediction rules to produce a strong composite estimator, with the underlying intuition that one can obtain accurate prediction rules by combining "rough" ones. Although boosting is proved to be consistent and overfitting-resistant, its numerical convergence rate is relatively slow. The aim of this paper is to develop a new boosting strategy, called the re-scale boosting (RBoosting), to accelerate the numerical convergence rate and, consequently, improve the learning performance of boosting. Our studies show that RBoosting possesses the almost optimal numerical convergence rate in the sense that, up to a logarithmic factor, it can reach the minimax nonlinear approximation rate. We then use RBoosting to tackle both the classification and regression problems, and deduce a tight generalization error estimate. The theoretical and experimental results show that RBoosting outperforms boosting in terms of generalization.

Jinshan Zeng, Zhimin Peng, Shaobo Lin

In recent studies on sparse modeling, $l_q$ ($0<q<1$) regularized least squares regression ($l_q$LS) has received considerable attention due to its superiorities on sparsity-inducing and bias-reduction over the convex counterparts. In this paper, we propose a Gauss-Seidel iterative thresholding algorithm (called GAITA) for solution to this problem. Different from the classical iterative thresholding algorithms using the Jacobi updating rule, GAITA takes advantage of the Gauss-Seidel rule to update the coordinate coefficients. Under a mild condition, we can justify that the support set and sign of an arbitrary sequence generated by GAITA will converge within finite iterations. This convergence property together with the Kurdyka-Łojasiewicz property of ($l_q$LS) naturally yields the strong convergence of GAITA under the same condition as above, which is generally weaker than the condition for the convergence of the classical iterative thresholding algorithms. Furthermore, we demonstrate that GAITA converges to a local minimizer under certain additional conditions. A set of numerical experiments are provided to show the effectiveness, particularly, much faster convergence of GAITA as compared with the classical iterative thresholding algorithms.

Shaobo Lin, Xingping Sun, Zongben Xu et al.

Polynomial kernel regression is one of the standard and state-of-the-art learning strategies. However, as is well known, the choices of the degree of polynomial kernel and the regularization parameter are still open in the realm of model selection. The first aim of this paper is to develop a strategy to select these parameters. On one hand, based on the worst-case learning rate analysis, we show that the regularization term in polynomial kernel regression is not necessary. In other words, the regularization parameter can decrease arbitrarily fast when the degree of the polynomial kernel is suitable tuned. On the other hand,taking account of the implementation of the algorithm, the regularization term is required. Summarily, the effect of the regularization term in polynomial kernel regression is only to circumvent the " ill-condition" of the kernel matrix. Based on this, the second purpose of this paper is to propose a new model selection strategy, and then design an efficient learning algorithm. Both theoretical and experimental analysis show that the new strategy outperforms the previous one. Theoretically, we prove that the new learning strategy is almost optimal if the regression function is smooth. Experimentally, it is shown that the new strategy can significantly reduce the computational burden without loss of generalization capability.

Shaobo Lin

Needlets have been recognized as state-of-the-art tools to tackle spherical data, due to their excellent localization properties in both spacial and frequency domains. This paper considers developing kernel methods associated with the needlet kernel for nonparametric regression problems whose predictor variables are defined on a sphere. Due to the localization property in the frequency domain, we prove that the regularization parameter of the kernel ridge regression associated with the needlet kernel can decrease arbitrarily fast. A natural consequence is that the regularization term for the kernel ridge regression is not necessary in the sense of rate optimality. Based on the excellent localization property in the spacial domain further, we also prove that all the $l^{q}$ $(01\leq q < \infty)$ kernel regularization estimates associated with the needlet kernel, including the kernel lasso estimate and the kernel bridge estimate, possess almost the same generalization capability for a large range of regularization parameters in the sense of rate optimality. This finding tentatively reveals that, if the needlet kernel is utilized, then the choice of $q$ might not have a strong impact in terms of the generalization capability in some modeling contexts. From this perspective, $q$ can be arbitrarily specified, or specified merely by other no generalization criteria like smoothness, computational complexity, sparsity, etc..

Lin Xu, Shaobo Lin, Jinshan Zeng et al.

Orthogonal greedy learning (OGL) is a stepwise learning scheme that adds a new atom from a dictionary via the steepest gradient descent and build the estimator via orthogonal projecting the target function to the space spanned by the selected atoms in each greedy step. Here, "greed" means choosing a new atom according to the steepest gradient descent principle. OGL then avoids the overfitting/underfitting by selecting an appropriate iteration number. In this paper, we point out that the overfitting/underfitting can also be avoided via redefining "greed" in OGL. To this end, we introduce a new greedy metric, called $δ$-greedy thresholds, to refine "greed" and theoretically verifies its feasibility. Furthermore, we reveals that such a greedy metric can bring an adaptive termination rule on the premise of maintaining the prominent learning performance of OGL. Our results show that the steepest gradient descent is not the unique greedy metric of OGL and some other more suitable metric may lessen the hassle of model-selection of OGL.

Jian Fang, Shaobo Lin, Zongben Xu

We consider the approximation capability of orthogonal super greedy algorithms (OSGA) and its applications in supervised learning. OSGA is concerned with selecting more than one atoms in each iteration step, which, of course, greatly reduces the computational burden when compared with the conventional orthogonal greedy algorithm (OGA). We prove that even for function classes that are not the convex hull of the dictionary, OSGA does not degrade the approximation capability of OGA provided the dictionary is incoherent. Based on this, we deduce a tight generalization error bound for OSGA learning. Our results show that in the realm of supervised learning, OSGA provides a possibility to further reduce the computational burden of OGA in the premise of maintaining its prominent generalization capability.

Shaobo Lin, Jinshan Zeng, Jian Fang et al.

Regularization is a well recognized powerful strategy to improve the performance of a learning machine and $l^q$ regularization schemes with $0<q<\infty$ are central in use. It is known that different $q$ leads to different properties of the deduced estimators, say, $l^2$ regularization leads to smooth estimators while $l^1$ regularization leads to sparse estimators. Then, how does the generalization capabilities of $l^q$ regularization learning vary with $q$? In this paper, we study this problem in the framework of statistical learning theory and show that implementing $l^q$ coefficient regularization schemes in the sample dependent hypothesis space associated with Gaussian kernel can attain the same almost optimal learning rates for all $0<q<\infty$. That is, the upper and lower bounds of learning rates for $l^q$ regularization learning are asymptotically identical for all $0<q<\infty$. Our finding tentatively reveals that, in some modeling contexts, the choice of $q$ might not have a strong impact with respect to the generalization capability. From this perspective, $q$ can be arbitrarily specified, or specified merely by other no generalization criteria like smoothness, computational complexity, sparsity, etc..

Shaobo Lin, Chen Xu, Jingshan Zeng et al.

$l^q$-regularization has been demonstrated to be an attractive technique in machine learning and statistical modeling. It attempts to improve the generalization (prediction) capability of a machine (model) through appropriately shrinking its coefficients. The shape of a $l^q$ estimator differs in varying choices of the regularization order $q$. In particular, $l^1$ leads to the LASSO estimate, while $l^{2}$ corresponds to the smooth ridge regression. This makes the order $q$ a potential tuning parameter in applications. To facilitate the use of $l^{q}$-regularization, we intend to seek for a modeling strategy where an elaborative selection on $q$ is avoidable. In this spirit, we place our investigation within a general framework of $l^{q}$-regularized kernel learning under a sample dependent hypothesis space (SDHS). For a designated class of kernel functions, we show that all $l^{q}$ estimators for $0< q < \infty$ attain similar generalization error bounds. These estimated bounds are almost optimal in the sense that up to a logarithmic factor, the upper and lower bounds are asymptotically identical. This finding tentatively reveals that, in some modeling contexts, the choice of $q$ might not have a strong impact in terms of the generalization capability. From this perspective, $q$ can be arbitrarily specified, or specified merely by other no generalization criteria like smoothness, computational complexity, sparsity, etc..