conftrace_

online sgd

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sample complexity (2) stochastic gradient descent (2) lor a (1) correlation (1) convergence iterations (1) low-rank fine-tuning (1) rank-1 perturbation (1) student-teacher setting (1) margin halfspace (1) higher-order cumulant (1)

Papers

Low-rank fine-tuning lies between lazy training and feature learning COLT 2025 A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise NeurIPS 2024 Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks ICML 2024