Optimization

Centroid Approximation for Bootstrap: Improving Particle Quality at Inference ICML 2022 Certifiable Robot Design Optimization using Differentiable Programming RSS 2022 Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking EMNLP 2022 Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation ICLR 2022 Certifying Some Distributional Fairness with Subpopulation Decomposition NeurIPS 2022 Challenging Common Assumptions in Convex Reinforcement Learning NeurIPS 2022 Channel Balancing for Accurate Quantization of Winograd Convolutions CVPR 2022 Chaotic Dynamics are Intrinsic to Neural Network Training with SGD NeurIPS 2022 Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling AACL 2022 Characterizing the Efficiency vs. Accuracy Trade-off for Long-Context NLP Models ACL 2022 Choices Are Not Independent: Stackelberg Security Games with Nested Quantal Response Models AAAI 2022 Chromatic Correlation Clustering, Revisited NeurIPS 2022 Churn Reduction via Distillation ICLR 2022 Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization NeurIPS 2022 Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments ICML 2022 ClimbQ: Class Imbalanced Quantization Enabling Robustness on Efficient Inferences NeurIPS 2022 CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders NeurIPS 2022 Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise NeurIPS 2022 Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards EMNLP 2022 Closed-Form Diffeomorphic Transformations for Time Series Alignment ICML 2022 Closed-loop Network Performance Monitoring and Diagnosis with SpiderMon NSDI 2022 Clustering-based Mode Reduction for Markov Jump Systems L4DC 2022 Coarse-To-Fine Deep Video Coding With Hyperprior-Guided Mode Prediction CVPR 2022 Coherent Point Drift Revisited for Non-Rigid Shape Matching and Registration CVPR 2022 ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction NAACL 2022