Statistical Learning

Privately Learning Mixtures of Axis-Aligned Gaussians NeurIPS 2021 Probabilistic Robustness Quantification of Neural Networks AAAI 2021 Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking CVPR 2021 Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021 Provably Strict Generalisation Benefit for Invariance in Kernel Methods NeurIPS 2021 Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction ICML 2021 Putting a Compass on the Map of Elections IJCAI 2021 Quantifying and Reducing Bias in Maximum Likelihood Estimation of Structured Anomalies ICML 2021 Query complexity of least absolute deviation regression via robust uniform convergence COLT 2021 Rao-Blackwellised parallel MCMC AISTATS 2021 RaSE: Random Subspace Ensemble Classification JMLR 2021 Rate-Regularization and Generalization in Variational Autoencoders AISTATS 2021 Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections NeurIPS 2021 Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Models AISTATS 2021 Regression Discontinuity Design under Self-selection AISTATS 2021 Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021 Regularized ERM on random subspaces AISTATS 2021 Regularizing towards Causal Invariance: Linear Models with Proxies ICML 2021 Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease NeurIPS 2021 Reinforcement Learning with Trajectory Feedback AAAI 2021 Relative Deviation Margin Bounds ICML 2021 Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space NeurIPS 2021 Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance ACL 2021 Research Reproducibility as a Survival Analysis AAAI 2021 Results of the WMT21 Metrics Shared Task: Evaluating Metrics with Expert-based Human Evaluations on TED and News Domain EMNLP 2021