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

The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
Why Is Public Pretraining Necessary for Private Model Training? ICML 2023
Detecting Adversarial Samples through Sharpness of Loss Landscape ACL 2023
On skip connections and normalisation layers in deep optimisation NIPS 2023
Stable Nonconvex-Nonconcave Training via Linear Interpolation NIPS 2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity NIPS 2023
Better Loss Landscape Visualization for Deep Neural Networks with Trajectory Information ACML 2023
An Empirical Investigation of the Role of Pre-training in Lifelong Learning JMLR 2023
Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers ICCV 2023
Flatness-Aware Minimization for Domain Generalization ICCV 2023
Landscape Learning for Neural Network Inversion ICCV 2023
PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer EMNLP 2023
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization CVPR 2023
Randomized Adversarial Training via Taylor Expansion CVPR 2023
Make Landscape Flatter in Differentially Private Federated Learning CVPR 2023
Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition CVPR 2023
Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory NIPS 2023
Why Does Sharpness-Aware Minimization Generalize Better Than SGD? NIPS 2023
Sharpness-Aware Gradient Matching for Domain Generalization CVPR 2023
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning NIPS 2023
Symmetry Teleportation for Accelerated Optimization NIPS 2022
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022
Understanding Robust Overfitting of Adversarial Training and Beyond ICML 2022
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes NIPS 2022