Optimization

(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NeurIPS 2023 Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability ICML 2023 SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization CVPR 2023 Solving Linear Programs with Fast Online Learning Algorithms ICML 2023 Solving stochastic weak Minty variational inequalities without increasing batch size ICLR 2023 SP2 : A Second Order Stochastic Polyak Method ICLR 2023 Sparse Bayesian optimization AISTATS 2023 Stable Nonconvex-Nonconcave Training via Linear Interpolation NeurIPS 2023 Stochastic Optimization under Distributional Drift JMLR 2023 T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization NeurIPS 2023 Target-based Surrogates for Stochastic Optimization ICML 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization ICLR 2023 Tighter Analysis for ProxSkip ICML 2023 Toward Large Kernel Models ICML 2023 Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models JMLR 2023 Training Deep Surrogate Models with Large Scale Online Learning ICML 2023 Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations AAAI 2023 Transformer-Based Learned Optimization CVPR 2023 Variational Inference with Gaussian Score Matching NeurIPS 2023 Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation ICLR 2023 Zeroth-order Optimization with Weak Dimension Dependency COLT 2023 Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis ICML 2022 Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always IJCAI 2022 Accelerated Projected Gradient Algorithms for Sparsity Constrained Optimization Problems NeurIPS 2022