Learning Theory

Algorithmic causal structure emerging through compression CLeaR 2025 Algorithms and Hardness for Active Learning on Graphs ICML 2025 Algorithms for ridge estimation with convergence guarantees JMLR 2025 Alignment of CNN and Human Judgments of Geometric and Topological Concepts AAAI 2025 Almost Sure Convergence of Dropout Algorithms for Neural Networks JMLR 2025 A Manifold Perspective on the Statistical Generalization of Graph Neural Networks ICML 2025 A Method for Enhancing Generalization of Adam by Multiple Integrations AAAI 2025 Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra ICLR 2025 Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels EMNLP 2025 Analyzing the Inner Workings of Transformers in Compositional Generalization NAACL 2025 Analyzing the Role of Permutation Invariance in Linear Mode Connectivity AISTATS 2025 An Analysis for Reasoning Bias of Language Models with Small Initialization ICML 2025 An Asymptotically Optimal Coordinate Descent Algorithm for Learning Bayesian Networks from Gaussian Models JMLR 2025 An Augmentation Overlap Theory of Contrastive Learning JMLR 2025 An Efficient Framework for Crediting Data Contributors of Diffusion Models ICLR 2025 An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications AISTATS 2025 A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledge IJCAI 2025 A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning ICML 2025 An in-depth human study of the mathematical reasoning abilities in Large Language Models EMNLP 2025 An Online Learning Theory of Trading-Volume Maximization ICLR 2025 An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints ICML 2025 An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks IJCAI 2025 A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators ICML 2025 A Novel Computational Modeling Foundation for Automatic Coherence Assessment NAACL 2025 An uncertainty principle for Linear Recurrent Neural Networks COLT 2025