gradient descent

Constrained Diffusion with Trust Sampling NeurIPS 2024 Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion COLT 2024 Curvature-Invariant Adversarial Attacks for 3D Point Clouds AAAI 2024 Deep linear networks for regression are implicitly regularized towards flat minima NeurIPS 2024 Diffeomorphic interpolation for efficient persistence-based topological optimization NeurIPS 2024 Differentiability and Optimization of Multiparameter Persistent Homology ICML 2024 Differentiable Combinatorial Scheduling at Scale ICML 2024 Differentially Private Optimization with Sparse Gradients NeurIPS 2024 Directional Smoothness and Gradient Methods: Convergence and Adaptivity NeurIPS 2024 Directly Fine-Tuning Diffusion Models on Differentiable Rewards ICLR 2024 DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction) AAAI 2024 Dropout Regularization Versus l2-Penalization in the Linear Model JMLR 2024 Dual Cone Gradient Descent for Training Physics-Informed Neural Networks NeurIPS 2024 EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration AAAI 2024 Estimating the Minimizer and the Minimum Value of a Regression Function under Passive Design JMLR 2024 Evolution and learning in differentiable robots RSS 2024 Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent AISTATS 2024 Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent AISTATS 2024 Faster Algorithms for User-Level Private Stochastic Convex Optimization NeurIPS 2024 Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations NeurIPS 2024 Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization NeurIPS 2024 FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning NeurIPS 2024 FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning CVPR 2024 Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond NeurIPS 2024 First-order ANIL provably learns representations despite overparametrisation ICLR 2024