Jingzhao Zhang

papers

351

total citations

papers (12)

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

NEURIPS 2023arXiv

citations

Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning

ICML 2024arXiv

citations

Efficient Sampling on Riemannian Manifolds via Langevin MCMC

NEURIPS 2022arXiv

citations

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

ICML 2025arXiv

citations

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

NEURIPS 2023arXiv

citations

Iteratively Learn Diverse Strategies with State Distance Information

NEURIPS 2023arXiv

citations

A Quadratic Synchronization Rule for Distributed Deep Learning

ICLR 2024arXiv

citations

Second-Order Min-Max Optimization with Lazy Hessians

ICLR 2025arXiv

citations

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition

NEURIPS 2025arXiv

citations

Jingzhao Zhang

papers (12)

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Why are Adaptive Methods Good for Attention Models?

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning

Efficient Sampling on Riemannian Manifolds via Langevin MCMC

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Iteratively Learn Diverse Strategies with State Distance Information

A Quadratic Synchronization Rule for Distributed Deep Learning

Second-Order Min-Max Optimization with Lazy Hessians

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition

papers (12)

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

Why are Adaptive Methods Good for Attention Models?

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning

Efficient Sampling on Riemannian Manifolds via Langevin MCMC

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Iteratively Learn Diverse Strategies with State Distance Information

A Quadratic Synchronization Rule for Distributed Deep Learning

Second-Order Min-Max Optimization with Lazy Hessians

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition