Optimization & Theory

Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis EMNLP 2022 NSGZero: Efficiently Learning Non-exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search AAAI 2022 NysADMM: faster composite convex optimization via low-rank approximation ICML 2022 OCSampler: Compressing Videos to One Clip With Single-Step Sampling CVPR 2022 ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation ACL 2022 Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again NeurIPS 2022 On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping JMLR 2022 On Biased Stochastic Gradient Estimation JMLR 2022 On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond NeurIPS 2022 On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NeurIPS 2022 On-Device Training Under 256KB Memory NeurIPS 2022 One-shot Neural Backdoor Erasing via Adversarial Weight Masking NeurIPS 2022 On global convergence of ResNets: From finite to infinite width using linear parameterization NeurIPS 2022 On Isotropy Calibration of Transformer Models ACL 2022 On Learning Fairness and Accuracy on Multiple Subgroups NeurIPS 2022 Online Convolutional Re-Parameterization CVPR 2022 Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking IJCAI 2022 On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning ICLR 2022 On Measuring Excess Capacity in Neural Networks NeurIPS 2022 On Measuring the Intrinsic Few-Shot Hardness of Datasets EMNLP 2022 On Non-Linear operators for Geometric Deep Learning NeurIPS 2022 On Numerical Integration in Neural Ordinary Differential Equations ICML 2022 On Scrambling Phenomena for Randomly Initialized Recurrent Networks NeurIPS 2022 On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency ACL 2022 On the Convergence of Certified Robust Training with Interval Bound Propagation ICLR 2022