Learning Theory

Limitations of Autoregressive Models and Their Alternatives NAACL 2021 Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021 Linear Bandits on Uniformly Convex Sets JMLR 2021 Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models NeurIPS 2021 List Learning with Attribute Noise AISTATS 2021 Local Differential Privacy for Regret Minimization in Reinforcement Learning NeurIPS 2021 Locality defeats the curse of dimensionality in convolutional teacher-student scenarios NeurIPS 2021 Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels NeurIPS 2021 Logarithmic Regret for Reinforcement Learning with Linear Function Approximation ICML 2021 Logarithmic Regret in Feature-based Dynamic Pricing NeurIPS 2021 Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks NeurIPS 2021 Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries ICML 2021 Machine Unlearning via Algorithmic Stability COLT 2021 Majorizing Measures, Sequential Complexities, and Online Learning COLT 2021 Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little EMNLP 2021 Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination NeurIPS 2021 Measuring Generalization with Optimal Transport NeurIPS 2021 Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences ICML 2021 MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain ACL 2021 Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation EACL 2021 MetaGrad: Adaptation using Multiple Learning Rates in Online Learning JMLR 2021 Meta Learning Backpropagation And Improving It NeurIPS 2021 Meta-Learning of Structured Task Distributions in Humans and Machines ICLR 2021 Meta-learning with negative learning rates ICLR 2021 Meta-Thompson Sampling ICML 2021