Learning Theory

Active Treatment Effect Estimation via Limited Samples ICML 2025 Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning ICML 2025 Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection ICML 2025 Adaptively profiling models with task elicitation EMNLP 2025 ADDQ: Adaptive distributional double Q-learning ICML 2025 Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts ICML 2025 A Distributional-Lifting Theorem for PAC Learning COLT 2025 Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets ICML 2025 Adversarial Robust Generalization of Graph Neural Networks ICML 2025 Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees ICML 2025 Adversarial Robustness via Deformable Convolution with Stochasticity ICML 2025 Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data ICLR 2025 Adversarial Training for Graph Convolutional Networks: Stability and Generalization Analysis IJCAI 2025 Adversarial Training in High-Dimensional Regression: Generated Data and Neural Networks AISTATS 2025 A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks ICML 2025 A Fine-grained Characterization of PAC Learnability COLT 2025 A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control ICML 2025 A Formal Framework for Understanding Length Generalization in Transformers ICLR 2025 A Formal Theory of Optimal Learning with Experimental Results IJCAI 2025 Agnostic Learning of Arbitrary ReLU Activation under Gaussian Marginals COLT 2025 Agnostic Private Density Estimation for GMMs via List Global Stability ALT 2025 A Graph Enhanced Symbolic Discovery Framework For Efficient Logic Optimization ICLR 2025 A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs AISTATS 2025 A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning IJCAI 2025 Algorithm Development in Neural Networks: Insights from the Streaming Parity Task ICML 2025