Theory

Benchmarking Meta-embeddings: What Works and What Does Not EMNLP 2021 Benchmarking: Past, Present and Future ACL 2021 Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation NeurIPS 2021 Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021 Best-case lower bounds in online learning NeurIPS 2021 Better Bounds on the Adaptivity Gap of Influence Maximization under Full-adoption Feedback AAAI 2021 Beyond Perturbation Stability: LP Recovery Guarantees for MAP Inference on Noisy Stable Instances AISTATS 2021 Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning NeurIPS 2021 Bias-Free Scalable Gaussian Processes via Randomized Truncations ICML 2021 Bilinear Classes: A Structural Framework for Provable Generalization in RL ICML 2021 BooVI: Provably Efficient Bootstrapped Value Iteration NeurIPS 2021 Bounded Memory Active Learning through Enriched Queries COLT 2021 Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning NeurIPS 2021 Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021 Can Transformer Language Models Predict Psychometric Properties? ACL 2021 Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression NeurIPS 2021 Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference? ACL 2021 Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication NeurIPS 2021 Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021 Causal Effect Inference for Structured Treatments NeurIPS 2021 Center Smoothing: Certified Robustness for Networks with Structured Outputs NeurIPS 2021 Change Point Detection via Multivariate Singular Spectrum Analysis NeurIPS 2021 Change the World - How Hard Can that Be? On the Computational Complexity of Fixing Planning Models IJCAI 2021 Characterizing Deep Gaussian Processes via Nonlinear Recurrence Systems AAAI 2021 Characterizing the Gap Between Actor-Critic and Policy Gradient ICML 2021