Learning Theory

Task Shift: From Classification to Regression in Overparameterized Linear Models AISTATS 2025 Telling Peer Direct Effects from Indirect Effects in Observational Network Data ICML 2025 Temporal Scaling Law for Large Language Models EMNLP 2025 Testing Juntas and Junta Subclasses with Relative Error COLT 2025 Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning ICLR 2025 Test-time Correlation Alignment ICML 2025 The Bandit Whisperer: Communication Learning for Restless Bandits AAAI 2025 The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures ICLR 2025 The Complexity of Learning Sparse Superposed Features with Feedback ICML 2025 The Complexity of Sequential Prediction in Dynamical Systems L4DC 2025 The Computational Complexity of Circuit Discovery for Inner Interpretability ICLR 2025 The Crucial Role of Samplers in Online Direct Preference Optimization ICLR 2025 The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT EMNLP 2025 The impact of allocation strategies in subset learning on the expressive power of neural networks ICLR 2025 The Importance of Being Lazy: Scaling Limits of Continual Learning ICML 2025 The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models ICCV 2025 The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025 Theoretical Analysis of Evolutionary Algorithms with Quality Diversity for a Classical Path Planning Problem IJCAI 2025 Theoretical Analysis of Leave-one-out Cross Validation for Non-differentiable Penalties under High-dimensional Settings AISTATS 2025 Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization IJCAI 2025 Theoretical Limitations of Ensembles in the Age of Overparameterization ICML 2025 Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models ICML 2025 Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport ICML 2025 Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels CVPR 2025 Theory of Agreement-on-the-Line in Linear Models and Gaussian Data AISTATS 2025