Mingyue Xu

Yihao Zhen, Mingyue Xu, Qiang Wang et al.

Multi-Camera Multi-Target (MCMT) tracking aims to locate and associate the same targets across multiple camera views. Existing methods typically adopt a two-stage framework, involving single-camera tracking followed by inter-camera tracking. However, in this paradigm, multi-view information is used only to recover missed matches in the first stage, providing a limited contribution to overall tracking. To address this issue, we propose GMT, a global MCMT tracking framework that jointly exploits intra-view and inter-view cues for tracking. Specifically, instead of assigning trajectories independently for each view, we integrate the same historical targets across different views as global trajectories, thereby reformulating the two-stage tracking as a unified global-level trajectory-target association process. We introduce a Cross-View Feature Consistency Enhancement (CFCE) module to align visual and spatial features across views, providing a consistent feature space for global trajectory modeling. With these aligned features, the Global Trajectory Association (GTA) module associates new detections with existing global trajectories, enabling direct use of multi-view information. Compared to the two-stage framework, GMT achieves significant improvements on existing datasets, with gains of up to 21.3 percent in CVMA and 17.2 percent in CVIDF1. Furthermore, we introduce VisionTrack, a high-quality, large-scale MCMT dataset providing significantly greater diversity than existing datasets. Our code and dataset will be released.

Mingyue Xu, Gal Vardi, Itay Safran

We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized linear regression models using gradient descent with weight decay. Specifically, we prove that the following stages occur: (i) the model overfits the training data early during training; (ii) poor generalization persists long after overfitting has manifested; and (iii) the generalization error eventually becomes arbitrarily small. Moreover, we show, both theoretically and empirically, that grokking can be amplified or eliminated in a principled manner through proper hyperparameter tuning. To the best of our knowledge, these are the first rigorous quantitative bounds on the generalization delay (which we refer to as the "grokking time") in terms of training hyperparameters. Lastly, going beyond the linear setting, we empirically demonstrate that our quantitative bounds also capture the behavior of grokking on non-linear neural networks. Our results suggest that grokking is not an inherent failure mode of deep learning, but rather a consequence of specific training conditions, and thus does not require fundamental changes to the model architecture or learning algorithm to avoid.

Jiyuan Tu, Weidong Liu, Xiaojun Mao et al.

The debiased estimator is a crucial tool in statistical inference for high-dimensional model parameters. However, constructing such an estimator involves estimating the high-dimensional inverse Hessian matrix, incurring significant computational costs. This challenge becomes particularly acute in distributed setups, where traditional methods necessitate computing a debiased estimator on every machine. This becomes unwieldy, especially with a large number of machines. In this paper, we delve into semi-supervised sparse statistical inference in a distributed setup. An efficient multi-round distributed debiased estimator, which integrates both labeled and unlabelled data, is developed. We will show that the additional unlabeled data helps to improve the statistical rate of each round of iteration. Our approach offers tailored debiasing methods for $M$-estimation and generalized linear models according to the specific form of the loss function. Our method also applies to a non-smooth loss like absolute deviation loss. Furthermore, our algorithm is computationally efficient since it requires only one estimation of a high-dimensional inverse covariance matrix. We demonstrate the effectiveness of our method by presenting simulation studies and real data applications that highlight the benefits of incorporating unlabeled data.

Shiben Liu, Mingyue Xu, Huijie Fan et al.

Lifelong person re-identification (LReID) encounters a key challenge: balancing the preservation of old knowledge with adaptation to new information. Existing LReID methods typically employ knowledge distillation to enforce representation alignment. However, these approaches ignore two crucial aspects: specific distribution awareness and cross-domain unified knowledge learning, both of which are essential for addressing this challenge. To overcome these limitations, we propose a novel distribution-aware knowledge unification and association (DKUA) framework where domain-style modeling is performed for each instance to propagate domain-specific representations, enhancing anti-forgetting and generalization capacity. Specifically, we design a distribution-aware model to transfer instance-level representations of the current domain into the domain-specific representations with the different domain styles, preserving learned knowledge without storing old samples. Next, we propose adaptive knowledge consolidation (AKC) to dynamically generate the unified representation as a cross-domain representation center. To further mitigate forgetting, we develop a unified knowledge association (UKA) mechanism, which explores the unified representation as a bridge to explicitly model inter-domain associations, reducing inter-domain gaps. Finally, distribution-based knowledge transfer (DKT) is proposed to prevent the current domain distribution from deviating from the cross-domain distribution center, improving adaptation capacity. Experimental results show our DKUA outperforms the existing methods by 7.6%/5.3% average mAP/R@1 improvement on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/LiuShiBen/DKUA.

Steve Hanneke, Mingyue Xu

Multitask learning and related frameworks have achieved tremendous success in modern applications. In multitask learning problem, we are given a set of heterogeneous datasets collected from related source tasks and hope to enhance the performance above what we could hope to achieve by solving each of them individually. The recent work of arXiv:2006.15785 has showed that, without access to distributional information, no algorithm based on aggregating samples alone can guarantee optimal risk as long as the sample size per task is bounded. In this paper, we focus on understanding the statistical limits of multitask learning. We go beyond the no-free-lunch theorem in arXiv:2006.15785 by establishing a stronger impossibility result of adaptation that holds for arbitrarily large sample size per task. This improvement conveys an important message that the hardness of multitask learning cannot be overcame by having abundant data per task. We also discuss the notion of optimal adaptivity that may be of future interests.

Gan Yuan, Mingyue Xu, Samory Kpotufe et al.

We consider the problem of sufficient dimension reduction (SDR) for multi-index models. The estimators of the central mean subspace in prior works either have slow (non-parametric) convergence rates, or rely on stringent distributional conditions (e.g., the covariate distribution $P_{\mathbf{X}}$ being elliptical symmetric). In this paper, we show that a fast parametric convergence rate of form $C_d \cdot n^{-1/2}$ is achievable via estimating the \emph{expected smoothed gradient outer product}, for a general class of distribution $P_{\mathbf{X}}$ admitting Gaussian or heavier distributions. When the link function is a polynomial with a degree of at most $r$ and $P_{\mathbf{X}}$ is the standard Gaussian, we show that the prefactor depends on the ambient dimension $d$ as $C_d \propto d^r$.

Kepu Zhang, Guofu Xie, Weijie Yu et al.

Legal mathematical reasoning is essential for applying large language models (LLMs) in high-stakes legal contexts, where outputs must be both mathematically accurate and procedurally compliant. However, existing legal LLMs lack structured numerical reasoning, and open-domain models, though capable of calculations, often overlook mandatory legal steps. To address this, we present LexNum, the first Chinese legal mathematical reasoning benchmark, covering three representative scenarios where each instance reflects legally grounded procedural flows. We further propose LexPam, a two-stage reinforcement learning framework for efficient legal reasoning training. Leveraging curriculum learning, we use a stronger teacher model to partition data into basic and challenging subsets. A lightweight 1.5B student model is then fine-tuned with Group Relative Policy Optimization, which avoids costly value networks and enables stable training from sparse, end-of-sequence rewards. The first stage improves accuracy and format; the second introduces a novel reward to guide procedural alignment via task-specific legal elements. Experiments show that existing models perform poorly on LexNum, while LexPam enhances both mathematical accuracy and legal coherence, and generalizes effectively across tasks and domains.

Jun Chen, Xinke Li, Mingyue Xu et al.

Gradient-based adversarial attacks have become a dominant approach for evaluating the robustness of point cloud classification models. However, existing methods often rely on uniform update rules that fail to consider the heterogeneous nature of point clouds, resulting in excessive and perceptible perturbations. In this paper, we rethink the design of gradient-based attacks by analyzing the limitations of conventional gradient update mechanisms and propose two new strategies to improve both attack effectiveness and imperceptibility. First, we introduce WAAttack, a novel framework that incorporates weighted gradients and an adaptive step-size strategy to account for the non-uniform contribution of points during optimization. This approach enables more targeted and subtle perturbations by dynamically adjusting updates according to the local structure and sensitivity of each point. Second, we propose SubAttack, a complementary strategy that decomposes the point cloud into subsets and focuses perturbation efforts on structurally critical regions. Together, these methods represent a principled rethinking of gradient-based adversarial attacks for 3D point cloud classification. Extensive experiments demonstrate that our approach outperforms state-of-the-art baselines in generating highly imperceptible adversarial examples. Code will be released upon paper acceptance.

Steve Hanneke, Mingyue Xu

The well-known empirical risk minimization (ERM) principle is the basis of many widely used machine learning algorithms, and plays an essential role in the classical PAC theory. A common description of a learning algorithm's performance is its so-called "learning curve", that is, the decay of the expected error as a function of the input sample size. As the PAC model fails to explain the behavior of learning curves, recent research has explored an alternative universal learning model and has ultimately revealed a distinction between optimal universal and uniform learning rates (Bousquet et al., 2021). However, a basic understanding of such differences with a particular focus on the ERM principle has yet to be developed. In this paper, we consider the problem of universal learning by ERM in the realizable case and study the possible universal rates. Our main result is a fundamental tetrachotomy: there are only four possible universal learning rates by ERM, namely, the learning curves of any concept class learnable by ERM decay either at $e^{-n}$, $1/n$, $\log(n)/n$, or arbitrarily slow rates. Moreover, we provide a complete characterization of which concept classes fall into each of these categories, via new complexity structures. We also develop new combinatorial dimensions which supply sharp asymptotically-valid constant factors for these rates, whenever possible.

Steve Hanneke, Mingyue Xu

The universal learning framework has been developed to obtain guarantees on the learning rates that hold for any fixed distribution, which can be much faster than the ones uniformly hold over all the distributions. Given that the Empirical Risk Minimization (ERM) principle being fundamental in the PAC theory and ubiquitous in practical machine learning, the recent work of arXiv:2412.02810 studied the universal rates of ERM for binary classification under the realizable setting. However, the assumption of realizability is too restrictive to hold in practice. Indeed, the majority of the literature on universal learning has focused on the realizable case, leaving the non-realizable case barely explored. In this paper, we consider the problem of universal learning by ERM for binary classification under the agnostic setting, where the ''learning curve" reflects the decay of the excess risk as the sample size increases. We explore the possibilities of agnostic universal rates and reveal a compact trichotomy: there are three possible agnostic universal rates of ERM, being either $e^{-n}$, $o(n^{-1/2})$, or arbitrarily slow. We provide a complete characterization of which concept classes fall into each of these categories. Moreover, we also establish complete characterizations for the target-dependent universal rates as well as the Bayes-dependent universal rates.