Theory

Analysis of Kernel Mirror Prox for Measure Optimization AISTATS 2024 Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity ICLR 2024 Analysis of Using Sigmoid Loss for Contrastive Learning AISTATS 2024 Analyzing Generalization in Policy Networks: A Case Study with the Double-Integrator System AAAI 2024 Analyzing Interpretability of Summarization Model with Eye-gaze Information COLING 2024 An Analysis of Tokenization: Transformers under Markov Data NeurIPS 2024 An Approximate Skolem Function Counter AAAI 2024 A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise NeurIPS 2024 An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates JMLR 2024 An Empirical Investigation Into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification WACV 2024 A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning NeurIPS 2024 An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem NeurIPS 2024 An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics EACL 2024 An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks ICML 2024 An information-theoretic lower bound in time-uniform estimation COLT 2024 An Information Theoretic Perspective on Conformal Prediction NeurIPS 2024 Anisotropy is Not Inherent to Transformers NAACL 2024 An L* Algorithm for Deterministic Weighted Regular Languages EMNLP 2024 A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios EMNLP 2024 Anvil: Verifying Liveness of Cluster Management Controllers OSDI 2024 Any-dimensional equivariant neural networks AISTATS 2024 Anytime-Constrained Reinforcement Learning AISTATS 2024 A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs ICLR 2024 Approximate Attributions for Off-the-Shelf Siamese Transformers EACL 2024 Approximately Piecewise E(3) Equivariant Point Networks ICLR 2024