Jingzhao Zhang

Faster Newton Methods for Convex and Nonconvex Optimization in Gradient Complexity COLT 2026 Fast and Multiphase Rates for Nearest Neighbor Classifiers COLT 2025 From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency ICLR 2025 Generalization Lower Bounds for GD and SGD in Smooth Stochastic Convex Optimization AISTATS 2025 Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles JMLR 2025 Scalable Model Merging with Progressive Layer-wise Distillation ICML 2025 Second-Order Min-Max Optimization with Lazy Hessians ICLR 2025 Solving Convex-Concave Problems with O(ε^-4/7) Second-Order Oracle Complexity COLT 2025 Task Generalization with Autoregressive Compositional Structure: Can Learning from D Tasks Generalize to D^T Tasks? ICML 2025 Towards Black-Box Membership Inference Attack for Diffusion Models ICML 2025 Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025 A Quadratic Synchronization Rule for Distributed Deep Learning ICLR 2024 Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem NeurIPS 2024 On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis COLT 2024 Online Control with Adversarial Disturbance for Continuous-time Linear Systems NeurIPS 2024 Online Policy Optimization for Robust Markov Decision Process UAI 2024 Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning ICML 2024 Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models ICLR 2023 Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions NeurIPS 2023 Iteratively Learn Diverse Strategies with State Distance Information NeurIPS 2023 On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective NeurIPS 2023 Beyond Worst-Case Analysis in Stochastic Approximation: Moment Estimation Improves Instance Complexity ICML 2022 Efficient Sampling on Riemannian Manifolds via Langevin MCMC NeurIPS 2022 Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022 Understanding the unstable convergence of gradient descent ICML 2022 Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization NeurIPS 2021 Coping with Label Shift via Distributionally Robust Optimisation ICLR 2021 Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? EMNLP 2021 Fast Federated Learning in the Presence of Arbitrary Device Unavailability NeurIPS 2021 Provably Efficient Algorithms for Multi-Objective Competitive RL ICML 2021 Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions ICML 2020 Why are Adaptive Methods Good for Attention Models? NeurIPS 2020 Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity ICLR 2020 Direct Runge-Kutta Discretization Achieves Acceleration NeurIPS 2018