Optimization

SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023 SGD with Large Step Sizes Learns Sparse Features ICML 2023 SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization Interspeech 2023 Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers EACL 2023 Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation JMLR 2023 Sharper Bounds for ℓ_p Sensitivity Sampling ICML 2023 Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes COLT 2023 Sharpness-Aware Gradient Matching for Domain Generalization CVPR 2023 Sharpness-Aware Minimization Leads to Low-Rank Features NeurIPS 2023 ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer NeurIPS 2023 ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories AAAI 2023 ShiftNAS: Improving One-shot NAS via Probability Shift ICCV 2023 Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search ICML 2023 Short-term Extrapolation of Speech Signals Using Recursive Neural Networks in the STFT Domain Interspeech 2023 Show Me the Way! Bilevel Search for Synthesizing Programmatic Strategies AAAI 2023 SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning NeurIPS 2023 Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities NeurIPS 2023 SIMPLE: A Gradient Estimator for k-Subset Sampling ICLR 2023 Simple Hardware-Efficient PCFGs with Independent Left and Right Productions EMNLP 2023 Simple, Scalable and Effective Clustering via One-Dimensional Projections NeurIPS 2023 SIMPLE: Specialized Model-Sample Matching for Domain Generalization ICLR 2023 Simplified State Space Layers for Sequence Modeling ICLR 2023 Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning ICML 2023 Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization NeurIPS 2023 Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions NeurIPS 2023