conftrace_

loss landscape

149 papers

Explore in graph

Co-occurring keywords

neural network optimization (1293) gradient descent (1144) neural network (6616) sharpness-aware minimization (81) stochastic gradient descent (1091) flat minima (50) deep neural network (1803) mode connectivity (17) transfer learning (5449) neural network training (309)

Papers

Revisiting Catastrophic Forgetting in Large Language Model Tuning EMNLP 2024
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition NIPS 2024
Stepping Forward on the Last Mile NIPS 2024
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024
Make Continual Learning Stronger via C-Flat NIPS 2024
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements NIPS 2024
Generalization Measures for Zero-Shot Cross-Lingual Transfer EMNLP 2024
LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate AAAI 2024
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective NIPS 2024
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training NIPS 2024
Why are Sensitive Functions Hard for Transformers? ACL 2024
Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning CVPR 2024
CR-SAM: Curvature Regularized Sharpness-Aware Minimization AAAI 2024
Unraveling the Gradient Descent Dynamics of Transformers NIPS 2024
Understanding the Generalization Benefits of Late Learning Rate Decay AISTATS 2024
In Search of a Data Transformation That Accelerates Neural Field Training CVPR 2024
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks NIPS 2024
Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization CVPR 2023
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation CVPR 2023
Spurious Valleys and Clustering Behavior of Neural Networks ICML 2023
Understanding Plasticity in Neural Networks ICML 2023
Which Shortcut Solution Do Question Answering Models Prefer to Learn? AAAI 2023
Mechanistic Mode Connectivity ICML 2023
An Empirical Investigation of the Role of Pre-training in Lifelong Learning JMLR 2023
PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer EMNLP 2023