conftrace_

flat minima

50 papers

Explore in graph

Co-occurring keywords

sharpness-aware minimization (81) neural network optimization (1293) loss landscape (149) stochastic gradient descent (1091) flat minimum (15) implicit bia (107) generalization bound (652) neural network (6616) model generalization (190) generalization error (285)

Papers

Sharpness-Aware Gradient Matching for Domain Generalization CVPR 2023
Randomized Adversarial Training via Taylor Expansion CVPR 2023
Differentially Private Sharpness-Aware Training ICML 2023
The alignment property of SGD noise and how it helps select flat minima: A stability analysis NIPS 2022
When Do Flat Minima Optimizers Work? NIPS 2022
Fisher SAM: Information Geometry and Sharpness Aware Minimisation ICML 2022
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data NIPS 2022
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging EMNLP 2022
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022
ROSE: Robust Selective Fine-tuning for Pre-trained Language Models EMNLP 2022
Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning ICML 2022
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022
Towards Understanding Sharpness-Aware Minimization ICML 2022
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization AISTATS 2021
Regularising Fisher Information Improves Cross-lingual Generalisation EMNLP 2021
SWAD: Domain Generalization by Seeking Flat Minima NIPS 2021
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima NIPS 2021
Relating Adversarially Robust Generalization to Flat Minima ICCV 2021
Regularizing Neural Networks via Adversarial Model Perturbation CVPR 2021
On Linear Stability of SGD and Input-Smoothness of Neural Networks NIPS 2021
Unique Properties of Flat Minima in Deep Networks ICML 2020
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning NIPS 2020
HLHLp: Quantized Neural Networks Training for Reaching Flat Minima in Loss Surface AAAI 2020
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis ICML 2020
Sharp Minima Can Generalize For Deep Nets ICML 2017