Theory

Parameterized Approximation Algorithms for Sum of Radii Clustering and Variants AAAI 2024 PE: A Poincare Explanation Method for Fast Text Hierarchy Generation EMNLP 2024 Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees NeurIPS 2024 Physics-Informed Neural Networks: Minimizing Residual Loss with Wide Networks and Effective Activations IJCAI 2024 Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings ICLR 2024 Policy Aggregation NeurIPS 2024 Polyhedral Complex Derivation from Piecewise Trilinear Networks NeurIPS 2024 Polynomial Width is Sufficient for Set Representation with High-dimensional Features ICLR 2024 Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure NeurIPS 2024 Position: Future Directions in the Theory of Graph Machine Learning ICML 2024 Post-Regularization Confidence Bands for Ordinary Differential Equations JMLR 2024 Predicting Emergent Abilities with Infinite Resolution Evaluation ICLR 2024 Predicting generalization performance with correctness discriminators EMNLP 2024 PRIME: Prioritizing Interpretability in Failure Mode Extraction ICLR 2024 Principles for AI-Assisted Social Influence and Their Application to Social Mediation EMNLP 2024 Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages ICML 2024 Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models ICLR 2024 Provable Benefits of Complex Parameterizations for Structured State Space Models NeurIPS 2024 Provable Partially Observable Reinforcement Learning with Privileged Information NeurIPS 2024 Provable Reward-Agnostic Preference-Based Reinforcement Learning ICLR 2024 Provable Robustness against a Union of L_0 Adversarial Attacks AAAI 2024 Provable Tempered Overfitting of Minimal Nets and Typical Nets NeurIPS 2024 Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples ICML 2024 Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes NeurIPS 2024 Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024