Xinhua Zhang

Xinhua Zhang, Lance R. Williams

Convolution is conventionally defined as a linear operation on functions of one or more variables which commutes with shifts. Group convolution generalizes the concept to linear operations on functions of group elements representing more general geometric transformations and which commute with those transformations. Since similarity transformation is the most general geometric transformation on images that preserves shape, the group convolution that is equivariant to similarity transformation is the most general shape preserving linear operator. Because similarity transformations have four free parameters, group convolutions are defined on four-dimensional, joint orientation-scale spaces. Although prior work on equivariant linear operators has been limited to discrete groups, the similarity group is continuous. In this paper, we describe linear operators on discrete representations that are equivariant to continuous similarity transformation. This is achieved by using a basis of functions that is it joint shiftable-twistable-scalable. These pinwheel functions use Fourier series in the orientation dimension and Laplace transform in the log-scale dimension to form a basis of spatially localized functions that can be continuously interpolated in position, orientation and scale. Although this result is potentially significant with respect to visual computation generally, we present an initial demonstration of its utility by using it to compute a shape equivariant distribution of closed contours traced by particles undergoing Brownian motion in velocity. The contours are constrained by sets of points and line endings representing well known bistable illusory contour inducing patterns.

Xinhua Zhang, Lance R. Williams

Because the magnitude of inner products with its basis functions are invariant to rotation and scale change, the Fourier-Mellin transform has long been used as a component in Euclidean invariant 2D shape recognition systems. Yet Fourier-Mellin transform magnitudes are only invariant to rotation and scale changes about a known center point, and full Euclidean invariant shape recognition is not possible except when this center point can be consistently and accurately identified. In this paper, we describe a system where a Fourier-Mellin transform is computed at every point in the image. The spatial support of the Fourier-Mellin basis functions is made local by multiplying them with a polynomial envelope. Significantly, the magnitudes of convolutions with these complex filters at isolated points are not (by themselves) used as features for Euclidean invariant shape recognition because reliable discrimination would require filters with spatial support large enough to fully encompass the shapes. Instead, we rely on the fact that normalized histograms of magnitudes are fully Euclidean invariant. We demonstrate a system based on the VLAD machine learning method that performs Euclidean invariant recognition of 2D shapes and requires an order of magnitude less training data than comparable methods based on convolutional neural networks.

Yingyi Ma, Vignesh Ganapathiraman, Yaoliang Yu et al.

Invariance (defined in a general sense) has been one of the most effective priors for representation learning. Direct factorization of parametric models is feasible only for a small range of invariances, while regularization approaches, despite improved generality, lead to nonconvex optimization. In this work, we develop a convex representation learning algorithm for a variety of generalized invariances that can be modeled as semi-norms. Novel Euclidean embeddings are introduced for kernel representers in a semi-inner-product space, and approximation bounds are established. This allows invariant representations to be learned efficiently and effectively as confirmed in our experiments, along with accurate predictions.

Zac Cranko, Zhan Shi, Xinhua Zhang et al.

The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators. In response, we give a very general equality result regarding the relationship between distributional robustness and regularisation, as defined with a transportation cost uncertainty set. The theory allows us to (tightly) certify the robustness properties of a Lipschitz-regularised model with very mild assumptions. As a theoretical application we show a new result explicating the connection between adversarial learning and distributional robustness. We then give new results for how to achieve Lipschitz regularisation of kernel classifiers, which are demonstrated experimentally.

Rizal Fathony, Kaiser Asif, Anqi Liu et al.

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) match the statistics of the training data. Although the optimized loss metrics are non-convex and non-continuous, the dual formulation of the framework is a convex optimization problem that can be recast as a risk minimization model with a prescribed convex surrogate loss we call the adversarial surrogate loss. We show that the adversarial surrogate losses fill an existing gap in surrogate loss construction for general multiclass classification problems, by simultaneously aligning better with the original multiclass loss, guaranteeing Fisher consistency, enabling a way to incorporate rich feature spaces via the kernel trick, and providing competitive performance in practice.

Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri et al.

In many structured prediction problems, complex relationships between variables are compactly defined using graphical structures. The most prevalent graphical prediction methods---probabilistic graphical models and large margin methods---have their own distinct strengths but also possess significant drawbacks. Conditional random fields (CRFs) are Fisher consistent, but they do not permit integration of customized loss metrics into their learning process. Large-margin models, such as structured support vector machines (SSVMs), have the flexibility to incorporate customized loss metrics, but lack Fisher consistency guarantees. We present adversarial graphical models (AGM), a distributionally robust approach for constructing a predictor that performs robustly for a class of data distributions defined using a graphical structure. Our approach enjoys both the flexibility of incorporating customized loss metrics into its design as well as the statistical guarantee of Fisher consistency. We present exact learning and prediction algorithms for AGM with time complexity similar to existing graphical models and show the practical benefits of our approach with experiments.

Shin Matsushima, Hyokun Yun, Xinhua Zhang et al.

Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many existing stochastic optimization algorithms cannot be parallelized efficiently. In this paper we show that one can rewrite the regularized risk minimization problem as an equivalent saddle-point problem, and propose an efficient distributed stochastic optimization (DSO) algorithm. We prove the algorithm's rate of convergence; remarkably, our analysis shows that the algorithm scales almost linearly with the number of processors. We also verify with empirical evaluations that the proposed algorithm is competitive with other parallel, general purpose stochastic and batch optimization algorithms for regularized risk minimization.

Hao Cheng, Xinhua Zhang, Dale Schuurmans

Although many convex relaxations of clustering have been proposed in the past decade, current formulations remain restricted to spherical Gaussian or discriminative models and are susceptible to imbalanced clusters. To address these shortcomings, we propose a new class of convex relaxations that can be flexibly applied to more general forms of Bregman divergence clustering. By basing these new formulations on normalized equivalence relations we retain additional control on relaxation quality, which allows improvement in clustering quality. We furthermore develop optimization methods that improve scalability by exploiting recent implicit matrix norm methods. In practice, we find that the new formulations are able to efficiently produce tighter clusterings that improve the accuracy of state of the art methods.