Theory

An Analytical Theory of Curriculum Learning in Teacher-Student Networks NeurIPS 2022 An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings ICML 2022 A Native Qualitative Numeric Planning Solver Based on AND/OR Graph Search IJCAI 2022 An EF2X Allocation Protocol for Restricted Additive Valuations IJCAI 2022 An Empirical study to understand the Compositional Prowess of Neural Dialog Models ACL 2022 An Encoder Attribution Analysis for Dense Passage Retriever in Open-Domain Question Answering NAACL 2022 An Equivalence Between Data Poisoning and Byzantine Gradient Attacks ICML 2022 An Error Analysis of Generative Adversarial Networks for Learning Distributions JMLR 2022 A Neural Tangent Kernel Perspective of GANs ICML 2022 A Neural Tangent Kernel Perspective of Infinite Tree Ensembles ICLR 2022 An Evaluative Measure of Clustering Methods Incorporating Hyperparameter Sensitivity AAAI 2022 A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?" ICLR 2022 An Experimental Design Approach for Regret Minimization in Logistic Bandits AAAI 2022 An Information-Theoretic Justification for Model Pruning AISTATS 2022 An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022 Anisotropic Random Feature Regression in High Dimensions ICLR 2022 Annihilation of Spurious Minima in Two-Layer ReLU Networks NeurIPS 2022 A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models NeurIPS 2022 A Novel Graph Aggregation Method Based on Feature Distribution Around Each Ego-node for Heterophily ACML 2022 An Unconstrained Layer-Peeled Perspective on Neural Collapse ICLR 2022 A Perturbation-Based Kernel Approximation Framework JMLR 2022 Approximate Cluster Recovery from Noisy Labels COLT 2022 Approximate Value Equivalence NeurIPS 2022 Approximation with CNNs in Sobolev Space: with Applications to Classification NeurIPS 2022 A Practical, Progressively-Expressive GNN NeurIPS 2022