Learning Theory

Best Arm Identification with Retroactively Increased Sampling Budget for More Resource-Efficient HPO IJCAI 2024 Best-of-Both-Worlds Algorithms for Linear Contextual Bandits AISTATS 2024 Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective AISTATS 2024 Better-than-KL PAC-Bayes Bounds COLT 2024 Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants’ API Invocation Capabilities COLING 2024 Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024 Binary Search with Distributional Predictions NeurIPS 2024 Black-Box k-to-1-PCA Reductions: Theory and Applications COLT 2024 BLADE: Benchmarking Language Model Agents for Data-Driven Science EMNLP 2024 Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval ACL 2024 Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data ICML 2024 Breadth-First Exploration on Adaptive Grid for Reinforcement Learning ICML 2024 Breaking through the learning plateaus of in-context learning in Transformer ICML 2024 Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses ICML 2024 Bridging the Empirical-Theoretical Gap in Neural Network Formal Language Learning Using Minimum Description Length ACL 2024 Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization COLT 2024 ByMI: Byzantine Machine Identification with False Discovery Rate Control ICML 2024 Byzantine Resilient and Fast Federated Few-Shot Learning ICML 2024 Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates ICML 2024 Can Biases in ImageNet Models Explain Generalization? CVPR 2024 Can Implicit Bias Imply Adversarial Robustness? ICML 2024 Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? EMNLP 2024 Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? ICML 2024 Can Transformers Learn n-gram Language Models? EMNLP 2024 CAP: A Context-Aware Neural Predictor for NAS IJCAI 2024