conftrace_

flatness regularization

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

learning to optimize (1) optimizer generalization (1) deep matrix factorization (1) parameter perturbation (1) schatten norm (1) large language model (1) hessian trace (1) flatness-aware regularization (1) gradient projection memory (1) weight loss landscape (1)

Papers

Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency EMNLP 2023 Learning to Generalize Provably in Learning to Optimize AISTATS 2023 What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models NeurIPS 2023 Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning NeurIPS 2021