Learning Theory

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping AAAI 2024 Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input ICML 2024 Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms ICML 2024 Predefined Prototypes for Intra-Class Separation and Disentanglement Interspeech 2024 Predicting Emergent Abilities with Infinite Resolution Evaluation ICLR 2024 Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms NeurIPS 2024 Predictive Dynamic Fusion ICML 2024 Preference-based Pure Exploration NeurIPS 2024 Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context NeurIPS 2024 Pretraining with Random Noise for Fast and Robust Learning without Weight Transport NeurIPS 2024 Principles from Clinical Research for NLP Model Generalization NAACL 2024 PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses ICML 2024 Prior-dependent analysis of posterior sampling reinforcement learning with function approximation AISTATS 2024 PrIsing: Privacy-Preserving Peer Effect Estimation via Ising Model AISTATS 2024 Privacy Preserving Adaptive Experiment Design ICML 2024 Private PAC Learning May be Harder than Online Learning ALT 2024 Probably approximately correct stability of allocations in uncertain coalitional games with private sampling L4DC 2024 Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs COLT 2024 Prompt Gradient Projection for Continual Learning ICLR 2024 Prompting a Pretrained Transformer Can Be a Universal Approximator ICML 2024 ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs EMNLP 2024 Prospective Learning: Learning for a Dynamic Future NeurIPS 2024 Provable Acceleration of Nesterov’s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks IJCAI 2024 Provable Advantage in Quantum PAC Learning COLT 2024 Provable and Efficient Dataset Distillation for Kernel Ridge Regression NeurIPS 2024