gradient descent

On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023 Optimistic Meta-Gradients NeurIPS 2023 Optimization and Bayes: A Trade-off for Overparameterized Neural Networks NeurIPS 2023 Optimizing ROC Curves with a Sort-Based Surrogate Loss for Binary Classification and Changepoint Detection JMLR 2023 Optimizing Test-Time Query Representations for Dense Retrieval ACL 2023 Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold COLT 2023 OTOv2: Automatic, Generic, User-Friendly ICLR 2023 Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron COLT 2023 Parameterized Cost Volume for Stereo Matching ICCV 2023 Partial Matrix Completion NeurIPS 2023 Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction ICCV 2023 Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification JMLR 2023 Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs NeurIPS 2023 Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks NeurIPS 2023 QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning NeurIPS 2023 Random Feature Amplification: Feature Learning and Generalization in Neural Networks JMLR 2023 Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization NeurIPS 2023 Regression as Classification: Influence of Task Formulation on Neural Network Features AISTATS 2023 Restricted Strong Convexity of Deep Learning Models with Smooth Activations ICLR 2023 Riemannian Accelerated Gradient Methods via Extrapolation AISTATS 2023 RLEKF: An Optimizer for Deep Potential with Ab Initio Accuracy AAAI 2023 Robust Camera Pose Refinement for Multi-Resolution Hash Encoding ICML 2023 Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity NeurIPS 2023 Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond AISTATS 2023 Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability ICLR 2023