loss landscape

Stable Nonconvex-Nonconcave Training via Linear Interpolation NeurIPS 2023 Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow ICLR 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory NeurIPS 2023 Understanding Plasticity in Neural Networks ICML 2023 What shapes the loss landscape of self supervised learning? ICLR 2023 Which Shortcut Solution Do Question Answering Models Prefer to Learn? AAAI 2023 Why Does Sharpness-Aware Minimization Generalize Better Than SGD? NeurIPS 2023 Why Is Public Pretraining Necessary for Private Model Training? ICML 2023 Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation ICLR 2022 Annihilation of Spurious Minima in Two-Layer ReLU Networks NeurIPS 2022 A Reparametrization-Invariant Sharpness Measure Based on Information Geometry NeurIPS 2022 A Solver + Gradient Descent Training Algorithm for Deep Neural Networks IJCAI 2022 Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules NeurIPS 2022 Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness ICML 2022 Chaotic Dynamics are Intrinsic to Neural Network Training with SGD NeurIPS 2022 Critical Points in Quantum Generative Models ICLR 2022 Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry ICML 2022 Deep Reinforcement Learning Policies Learn Shared Adversarial Features across MDPs AAAI 2022 Exploring Mode Connectivity for Pre-trained Language Models EMNLP 2022 How Do Vision Transformers Work? ICLR 2022 How many degrees of freedom do we need to train deep networks: a loss landscape perspective ICLR 2022 Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks NeurIPS 2022 Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022 Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NeurIPS 2022