optimization dynamics

Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis CVPR 2026 Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data ACL 2026 Optimization and Robustness-Informed Membership Inference Attacks for LLMs AAAI 2026 Understanding Optimization in Deep Learning with Central Flows ICLR 2025 LEAD: Exploring Logit Space Evolution for Model Selection CVPR 2024 Why Do We Need Weight Decay in Modern Deep Learning? NeurIPS 2024 SAM operates far from home: eigenvalue regularization as a dynamical phenomenon ICML 2023 Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability ICLR 2023 Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NeurIPS 2023 Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks JMLR 2022 Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs NeurIPS 2022 Surprising Instabilities in Training Deep Networks and a Theoretical Analysis NeurIPS 2022 On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay NeurIPS 2021