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

Tractable Sharpness-Aware Learning of Probabilistic Circuits AAAI 2026
A Flat Minima Perspective on Understanding Augmentations and Model Robustness AAAI 2026
Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond AAAI 2026
Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations NAACL 2025
Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025
Understanding Flatness in Generative Models: Its Role and Benefits ICCV 2025
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes CVPR 2025
A Method for Enhancing Generalization of Adam by Multiple Integrations AAAI 2025
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models CVPR 2025
Where Do Large Learning Rates Lead Us? NIPS 2024
Towards Unsupervised Model Selection for Domain Adaptive Object Detection NIPS 2024
Improving Generalization and Convergence by Enhancing Implicit Regularization NIPS 2024
Deep linear networks for regression are implicitly regularized towards flat minima NIPS 2024
Make Continual Learning Stronger via C-Flat NIPS 2024
Why is parameter averaging beneficial in SGD? An objective smoothing perspective AISTATS 2024
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation CVPR 2023
An SDE for Modeling SAM: Theory and Insights ICML 2023
Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition CVPR 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023
Enhancing Sharpness-Aware Optimization Through Variance Suppression NIPS 2023
Boosting Adversarial Transferability by Achieving Flat Local Maxima NIPS 2023
Lookaround Optimizer: $k$ steps around, 1 step average NIPS 2023
Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks AAAI 2023
Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization CVPR 2023