| Publication | Date of Publication | Type |
|---|
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
Journal of the American Statistical Association | 2026-01-07 | Paper |
Matching Higher-Order Oracle Complexity for Smooth Monotone Variational Inequalities
(available as arXiv preprint) | 2026-01-01 | Paper |
Near-Optimal Deterministic Exact-Value Complexity for Smooth Convex Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Upper and Lower Bounds for Higher-Order Nonconvex Finite-Sum Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Second-Order Stationarity with Common Random Losses: Matching Tolerance Bounds
(available as arXiv preprint) | 2026-01-01 | Paper |
Near-Optimal Higher-Order Oracle Complexity for Convex--Concave Minimax Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Sharp Fresh-Gradient Complexity of Nonconvex-Strongly-Concave Minimax Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Lower Bounds for Randomized First-Order Methods in Hessian-Lipschitz Nonconvex Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Sharp High-Probability Statistical Rates for Heavy-Tailed Nonsmooth Convex Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Joint Lower Bounds for Zeroth-Order Nonconvex Optimization on Euclidean Balls
(available as arXiv preprint) | 2026-01-01 | Paper |
Sharp Minimax Rates for Highly Smooth Strongly Convex Zeroth-Order Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Closing the Accuracy Gap in Stochastic First-Order Bilevel Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
The Minimax Cost of Smoothness in Fully First-Order Stochastic Bilevel Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Geodesically Convex Optimization in Hyperbolic Space: Matching Lower Bounds
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Full-Hessian Oracle Complexity for Nonconvex--Strongly-Concave Minimax Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Complexity for Second-Order Stationary Point with Sample Reuse
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Randomized Bounds for Finite-Sum Nonconvex-Concave Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Matching Randomized First-Order Bounds for Higher-Order Smooth Nonconvex Optimization
(available as arXiv preprint) | 2026-01-01 | Paper |
Gradient-Hessian Query Tradeoffs: Matching Lower Bounds in Logarithmic Dimension
(available as arXiv preprint) | 2026-01-01 | Paper |
Causality pursuit from heterogeneous environments via neural adversarial invariance learning
The Annals of Statistics | 2025-12-02 | Paper |
Exploring deep neural networks via layer-peeled model: minority collapse in imbalanced training
Proceedings of the National Academy of Sciences of the United States of America | 2025-03-05 | Paper |
Environment invariant linear least squares
The Annals of Statistics | 2025-01-03 | Paper |
Near-Optimal Tensor PCA via Normalized Stochastic Gradient Ascent with Overparameterization
(available as arXiv preprint) | 2025-01-01 | Paper |
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
(available as arXiv preprint) | 2024-01-01 | Paper |
| Zeroth-order Optimization with Weak Dimension Dependency | 2023-07-11 | Paper |
Zeroth-order Optimization with Weak Dimension Dependency
(available as arXiv preprint) | 2023-01-01 | Paper |
| On the Lower Bound of Minimizing Polyak-{\L}ojasiewicz Functions | 2022-12-27 | Paper |
Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
IEEE Transactions on Signal Processing | 2022-09-23 | Paper |
| Alternating direction method of multipliers for machine learning | 2022-05-19 | Paper |
On the Lower Bound of Minimizing Polyak-Łojasiewicz Functions
(available as arXiv preprint) | 2022-01-01 | Paper |
| Accelerated optimization for machine learning. First-order algorithms. With forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo | 2020-04-21 | Paper |
| Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations | 2019-10-24 | Paper |
Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations
(available as arXiv preprint) | 2019-01-01 | Paper |
| Convergence Rates Analysis of The Quadratic Penalty Method and Its Applications to Decentralized Distributed Optimization | 2017-11-29 | Paper |
| Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers | 2017-04-22 | Paper |
Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
(available as arXiv preprint) | 2017-01-01 | Paper |
Convergence Rates Analysis of The Quadratic Penalty Method and Its Applications to Decentralized Distributed Optimization
(available as arXiv preprint) | 2017-01-01 | Paper |
