Preprints (‘‘*’’ denotes equal contribution, ‘‘\(\dagger\)’’ denotes corresponding author, ‘‘\(\S\)’’ denotes my supervised students.)
Peng Wang*, Po Chen*, Rujun Jiang, Laura Balzano. Benign Landscape of Quadratic Programs with Orthogonality Constraints and Its Application to Heteroscedastic Probabilistic PCA, 2026. [paper]
Huikang Liu, Peng Wang\(^\dagger\), Laura Balzano. A Concentration Inequality for the Covariance Matrix of an Arbitrary Subset of Random Vectors, 2026. [paper]
Huijie Zhang, Zijian Huang, Siyi Chen, Jinfan Zhou, Zekai Zhang, Peng Wang, Qing Qu. Understanding Generalization in Diffusion Models via Probability Flow Distance, 2026. ICML Workshop on Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning [paper]
Can Yaras*, Peng Wang*, Wei Hu, Zhihui Zhu, Laura Balzano, Qing Qu. The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks, 2023. [paper]
Taoli Zheng, Peng Wang\(^\dagger\), Anthony Man-Cho So. A Linearly Convergent Algorithm for Rotationally Invariant L1-Norm Principal Component Analysis, 2022. [paper]
Books
Principles and Practice of Deep Representation Learning. Sam Buchanan, Druv Pai, Peng Wang, Yi Ma. An open source book, 2026. To be published in Cambridge University Press. [book, website]
Journal Papers
(\(\alpha\)-\(\beta\) order) Po Chen, Rujun Jiang, Peng Wang. Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks. Accepted for publication in Mathematics of Operations Research, 2026. [paper]
(\(\alpha\)-\(\beta\) order) Po Chen, Rujun Jiang, Peng Wang\(^\dagger\). A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization. Accepted for publication in SIAM Journal on Optimization, 2026. [paper]
Peng Wang*, Huijie Zhang*, Zekai Zhang, Siyi Chen, Yi Ma, Qing Qu. Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions. Journal of Machine Learning Research (2026) 27(179):1-50. [paper]
(\(\alpha\)-\(\beta\) order) Laura Balzano\(^\dagger\), Tianjiao Ding\(^\dagger\), Benjamin D. Haeffele, Soo Min Kwon, Qing Qu, Peng Wang\(^\dagger\), Zhangyang Wang, Can Yaras. An Overview of Low-Rank Structures in the Training and Adaptation of Large Models. IEEE Signal Processing Magazine (2026) 43(3): 52-70. [paper, code]
Peng Wang, Rujun Jiang, Qingyuan Kong, Laura Balzano. A Proximal Difference-of-Convex Algorithm for Sample Average Approximation of Chance Constrained Programming. INFORMS Journal on Computing (2026) 38(1): 315-339. [paper, code]
Peng Wang*\(^\dagger\), Xiao Li*, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu. Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination. Journal of Machine Learning Research (2025) 26(220):1-61. [paper, code]
Peng Wang, Huikang Liu, Anthony Man-Cho So. Linear Convergence of Proximal Alternating Minimization Method with Extrapolation for L1-Norm Principal Component Analysis. SIAM Journal on Optimization (2023) 33(2):684-712. [paper]
Peng Wang, Zirui Zhou, Anthony Man-Cho So. Non-Convex Exact Community Recovery in Stochastic Block Model. Mathematical Programming, Series A (2022) 195(1-2):793-829. [paper]
Conference Papers
Peng Wang*, Po Chen*, Huikang Liu, Rujun Jiang. A Local Geometric Analysis of Maximal Coding Rate Reduction via Error Bounds. NeurIPS 2026. [paper]
Yi Zhang, Peng Wang, Difan Zou. Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation. ICML 2026 (Best Paper Runner-up of ICML FoGen Workshop, acceptance rate: 3/230). [paper]
Alec S Xu, Can Yaras, Peng Wang, Qing Qu. Understanding How Nonlinear Layers Create Linearly Separable Features for Low-Dimensional Data. AISTATS 2026. [paper]
Xiao Li*, Zekai Zhang*, Xiang Li, Siyi Chen, Zhihui Zhu, Peng Wang\(^\dagger\), Qing Qu. Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling. NeurIPS 2025. [paper]
Peng Wang\(^\dagger\), Yifu Lu, Yaodong Yu, Druv Pai, Qing Qu, Yi Ma. Attention-Only Transformers via Unrolled Subspace Denoising. ICML 2025. [paper]
Can Yaras*, Siyi Chen*, Peng Wang, Qing Qu. Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning. CAPL 2025. [paper]
Siyi Chen*, Huijie Zhang*, Minzhe Guo, Yifu Lu, Peng Wang, Qing Qu. Exploring Low-Dimensional Subspaces in Diffusion Models for Controllable Image Editing. NeurIPS 2024. [paper]
Peng Wang, Huikang Liu, Druv Pai, Yaodong Yu, Zhihui Zhu, Qing Qu, Yi Ma. A Global Geometric Analysis of Maximal Coding Rate Reduction. ICML 2024. [paper]
Can Yaras, Peng Wang, Laura Balzano, Qing Qu. Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation. ICML 2024 (Oral, acceptance rate: 1.52%). [paper]
Huikang Liu*, Peng Wang*, Longxiu Huang, Qing Qu, Laura Balzano. Matrix Completion with ReLU Sampling. ICML 2024. [paper]
Jiachen Jiang, Jinxin Zhou, Peng Wang, Qing Qu, Dustin Mixon, Chong You, Zhihui Zhu. Generalized Neural Collapse for a Large Number of Classes. ICML 2024. [paper]
Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, and Qing Qu. The Emergence of Reproducibility and Consistency in
Diffusion Models. ICML 2024. [paper]
Jinxin Wang, Yuen-Man Pun, Xiaolu Wang, Peng Wang, Anthony Man-Cho So. Projected Tensor Power Method for Hypergraph Community Recovery. ICML 2023. [paper]
Can Yaras*, Peng Wang*, Zhihui Zhu, Laura Balzano, Qing Qu. Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold. NeurIPS 2022. [paper]
Peng Wang, Huikang Liu, Anthony Man-Cho So, Laura Balzano. Convergence and Recovery Guarantees of the K-Subspaces Method for Subspace Clustering. ICML 2022. [paper]
Xiaolu Wang, Peng Wang, Anthony Man-Cho So. Exact Community Recovery over Signed Graphs. AISTATS 2022. [paper]
Peng Wang, Huikang Liu, Zirui Zhou, Anthony Man-Cho So. Optimal Non-Convex Exact Recovery in Stochastic Block Model via Projected Power Method. ICML 2021. [paper]
Peng Wang*, Zirui Zhou*, Anthony Man-Cho So. A Nearly-Linear Time Algorithm for Exact Community Recovery in Stochastic Block Model. ICML 2020. [paper]
Peng Wang, Huikang Liu, Anthony Man-Cho So. Globally Convergent Accelerated Proximal Alternating Maximization Method for L1-Principal Component Analysis. ICASSP 2019 (IEEE SPS Student Travel Award). [paper]
Huikang Liu, Peng Wang, Anthony Man-Cho So. Fast First-Order Methods for the Massive Robust Multicast Beamforming Problem with Interference Temperature Constraints. ICASSP 2019. [paper]
Workshop Papers
Wendong Li\({}^{*\S}\), Huikang Liu*, Zhiyuan Huang, Po Chen, Rujun Jiang, Peng Wang. A Unified Perspective on Task Retrieval and Learning in In-Context Learning on Markov Data. ICML FoGen Workshop 2026. [paper] (Spotlight)
Can Yaras*, Peng Wang*, Wei Hu, Zhihui Zhu, Laura Balzano, Qing Qu. Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Matrix Factorizations. NeurIPS M3L Workshop 2023. [paper]
Peng Wang*, Huikang Liu*, Can Yaras*, Laura Balzano, Qing Qu. Linear Convergence Analysis of Neural Collapse with Unconstrained Features. NeurIPS Workshop on Optimization for Machine Learning, NeurIPS OPT Workshop 2022. [paper]
Newsletters
Huijie Zhang, Peng Wang, Siyi Chen, Zekai Zhang, Qing Qu. Generalization of Diffusion Models: Principles, Theory, and Implications. SIAM News, 2025. [blog]
|