Optimization

SGD Can Converge to Local Maxima ICLR 2022 SGD with Coordinate Sampling: Theory and Practice JMLR 2022 Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization Interspeech 2022 Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search CVPR 2022 Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality NeurIPS 2022 Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective AISTATS 2022 Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood ICML 2022 Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning NeurIPS 2022 Sharper Rates for Separable Minimax and Finite Sum Optimization via Primal-Dual Extragradient Methods COLT 2022 Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning ICML 2022 Sharpness-Aware Minimization Improves Language Model Generalization ACL 2022 Sharpness-Aware Minimization with Dynamic Reweighting EMNLP 2022 Sharpness-Aware Training for Free NeurIPS 2022 Sharp Restricted Isometry Property Bounds for Low-Rank Matrix Recovery Problems with Corrupted Measurements AAAI 2022 ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks ICML 2022 Shifted compression framework: generalizations and improvements UAI 2022 SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models ICLR 2022 Signal Recovery with Non-Expansive Generative Network Priors NeurIPS 2022 Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization JMLR 2022 Simulation-guided Beam Search for Neural Combinatorial Optimization NeurIPS 2022 Simultaneous Graph Signal Clustering and Graph Learning ICML 2022 Single Loop Gaussian Homotopy Method for Non-convex Optimization NeurIPS 2022 Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity NeurIPS 2022 Sketching Algorithms and Lower Bounds for Ridge Regression ICML 2022 Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences NAACL 2022