Skip to content
conftrace_

layer-wise perturbation

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sharpness-aware minimization (2) personalized federated learning (1) local optimization (1) infinite-width limit (1) perturbation scaling (1) variance explosion (1) explicit regularization (1) neural network generalization (1) overparameterized neural network (1) overparameterized model (1)

Papers

Flexible Sharpness-Aware Personalized Federated Learning AAAI 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 Explicit Regularization in Overparametrized Models via Noise Injection AISTATS 2023