Jingfeng Wu

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization

Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models

Improved Scaling Laws in Linear Regression via Data Reuse

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

How Does Critical Batch Size Scale in Pre-training?

Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks

Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes

Context-Scaling versus Task-Scaling in In-Context Learning