Optimization & Theory

Revisit last-iterate convergence of mSGD under milder requirement on step size NeurIPS 2022 ReX: An Efficient Approach to Reducing Memory Cost in Image Classification AAAI 2022 Richer Countries and Richer Representations ACL 2022 RID-Noise: Towards Robust Inverse Design under Noisy Environments AAAI 2022 RL with KL penalties is better viewed as Bayesian inference EMNLP 2022 Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks JMLR 2022 Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees ICML 2022 Robust Lottery Tickets for Pre-trained Language Models ACL 2022 Robustness Implies Generalization via Data-Dependent Generalization Bounds ICML 2022 Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NeurIPS 2022 Robustness to Unbounded Smoothness of Generalized SignSGD NeurIPS 2022 Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients CVPR 2022 Robust Training in High Dimensions via Block Coordinate Geometric Median Descent AISTATS 2022 ROOT-SGD: Sharp Nonasymptotics and Asymptotic Efficiency in a Single Algorithm COLT 2022 RSTT: Real-Time Spatial Temporal Transformer for Space-Time Video Super-Resolution CVPR 2022 RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer NeurIPS 2022 Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions NeurIPS 2022 SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems ACL 2022 Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs AAAI 2022 SAN: Stochastic Average Newton Algorithm for Minimizing Finite Sums AISTATS 2022 SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training NeurIPS 2022 Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy NeurIPS 2022 Scalable Interpretability via Polynomials NeurIPS 2022 Scaled ReLU Matters for Training Vision Transformers AAAI 2022 Scale Efficiently: Insights from Pretraining and Finetuning Transformers ICLR 2022