theoretical analysis

Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources ICML 2023 Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective NeurIPS 2023 Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks EACL 2023 Trade-off Between Efficiency and Consistency for Removal-based Explanations NeurIPS 2023 Understanding Representation Learnability of Nonlinear Self-Supervised Learning AAAI 2023 An Analysis of the Linear Bilateral ANAC Domains Using the MiCRO Benchmark Strategy IJCAI 2022 A Theoretical View on Sparsely Activated Networks NeurIPS 2022 A Tighter Analysis of Spectral Clustering, and Beyond ICML 2022 Estimation and Comparison of Linear Regions for ReLU Networks IJCAI 2022 Evaluation Methods for Representation Learning: A Survey IJCAI 2022 Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis AISTATS 2022 Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably? AISTATS 2022 Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods AISTATS 2022 Provable Guarantees for Understanding Out-of-Distribution Detection AAAI 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 The King Is Naked: On the Notion of Robustness for Natural Language Processing AAAI 2022 Towards Theoretically Grounded Evolutionary Learning IJCAI 2022 An Analysis of LIME for Text Data AISTATS 2021 A Theoretical Analysis of the Repetition Problem in Text Generation AAAI 2021 Contrastive Learning Inverts the Data Generating Process ICML 2021 On the Intrinsic Differential Privacy of Bagging IJCAI 2021 Representational aspects of depth and conditioning in normalizing flows ICML 2021 Reward Identification in Inverse Reinforcement Learning ICML 2021 A Critique of the Smooth Inverse Frequency Sentence Embeddings (Student Abstract) AAAI 2020 Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness AISTATS 2020