conftrace_

Jingzhao Zhang

33 papers · 2018–2025 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) πŸ—ΊοΈ Taxonomy Completionist (10) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (7)
πŸ—ΊοΈ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (7) 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (33) ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (98) ❓ The Questioner (3)

Conferences

ICML (10) NIPS (10) ICLR (6) COLT (3) AISTATS (1) EMNLP (1) JMLR (1) UAI (1)

Papers

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