learning theory

518 papers

Explore in graph

Co-occurring keywords

generalization bound (649) sample complexity (1158) statistical learning (350) neural network (6616) online learning (1770) gradient descent (1143) stochastic gradient descent (1088) empirical risk minimization (348) convergence rate (606) pac learning (280)

Papers

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds AAAI 2026

Memorization and Expressivity in Transformers: A Learning-Theoretic Perspective AAAI 2026

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms AAAI 2026

Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport (Abstract Reprint) AAAI 2026

Capacity Constraints Make Admissions Processes Less Predictable AAAI 2026

Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning AAAI 2026

Unified Structural Factors for Transfer Learning Generalization with PAC-Bayesian Guarantees AAAI 2026

Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden’s J statistic EACL 2026

On Coresets for End-to-end Learning from Crowds AAAI 2026

Cost-Sensitive Conformal Training with Provably Controllable Learning Bounds AAAI 2026

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs ACL 2025

Towards Improved Risk Bounds for Transductive Learning IJCAI 2025

Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound JMLR 2025

Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings COLING 2025

Statistical Deficiency for Task Inclusion Estimation ACL 2025

Instability, Computational Efficiency and Statistical Accuracy JMLR 2025

Learnability of Parameter-Bounded Bayes Nets AAAI 2025

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025

Convergence and Divergence of Language Models under Different Random Seeds EMNLP 2025

A Unified Interpretation of Training-Time Out-of-Distribution Detection ICCV 2025

The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT EMNLP 2025

Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology AAAI 2025

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning EMNLP 2025

Improved Sample Complexity for Multiclass PAC Learning NIPS 2024

The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems NIPS 2024