Learning Theory

PDUDT: Provable Decentralized Unlearning under Dynamic Topologies ICML 2025 PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity ICML 2025 Perfect Recovery for Random Geometric Graph Matching with Shallow Graph Neural Networks AISTATS 2025 Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws ICLR 2025 Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models ACL 2025 PlanningArena: A Modular Benchmark for Multidimensional Evaluation of Planning and Tool Learning ACL 2025 Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems ICML 2025 PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs ICLR 2025 Position: AI Competitions Provide the Gold Standard for Empirical Rigor in GenAI Evaluation ICML 2025 Positional Attention: Expressivity and Learnability of Algorithmic Computation ICML 2025 Position: All Current Generative Fidelity and Diversity Metrics are Flawed ICML 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025 Position: A Theory of Deep Learning Must Include Compositional Sparsity ICML 2025 Position: Constants are Critical in Regret Bounds for Reinforcement Learning ICML 2025 Position: Deep Learning is Not So Mysterious or Different ICML 2025 Position: Graph Matching Systems Deserve Better Benchmarks ICML 2025 Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings COLING 2025 Position: Lifetime tuning is incompatible with continual reinforcement learning ICML 2025 Posterior Concentrations of Fully-Connected Bayesian Neural Networks with General Priors on the Weights JMLR 2025 PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction CVPR 2025 Predicting quantum channels over general product distributions COLT 2025 Predicting the Susceptibility of Examples to Catastrophic Forgetting ICML 2025 Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors ICLR 2025 PreSumm: Predicting Summarization Performance Without Summarizing ACL 2025 Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents ICML 2025