← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination JMLR 2025
High-Dimensional L2-Boosting: Rate of Convergence JMLR 2025
An Augmentation Overlap Theory of Contrastive Learning JMLR 2025
Invariant Shape Representation Learning for Image Classification WACV 2025
Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization WACV 2025
CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations COLING 2025
Beyond Surprisal: A Dual Metric Framework for Lexical Skill Acquisition in LLMs COLING 2025
Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance? NAACL 2025
Language Models Encode Numbers Using Digit Representations in Base 10 NAACL 2025
Theoretical Analysis of Evolutionary Algorithms with Quality Diversity for a Classical Path Planning Problem IJCAI 2025
GCG-Based Artificial Languages for Evaluating Inductive Biases of Neural Language Models ACL 2025
Imprecise Multi-Armed Bandits: Representing Irreducible Uncertainty as a Zero-Sum Game JMLR 2025
Investigating the Zone of Proximal Development of Language Models for In-Context Learning NAACL 2025
Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERT ACL 2025
Shapley Value Computation in Ontology-Mediated Query Answering (Extended Abstract) IJCAI 2025
Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments ACL 2025
Improving Generalization in Meta-Learning via Meta-Gradient Augmentation IJCAI 2025
Global Convergence of Adjoint-Optimized Neural PDEs JMLR 2025
On the Generalization of Feature Incremental Learning IJCAI 2025
A Formal Theory of Optimal Learning with Experimental Results IJCAI 2025
LiBOG: Lifelong Learning for Black-Box Optimizer Generation IJCAI 2025
Almost Sure Convergence of Dropout Algorithms for Neural Networks JMLR 2025
On the Hardness of Training Deep Neural Networks Discretely AAAI 2025
There’s No Such Thing as Simple Reasoning for LLMs ACL 2025
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving EMNLP 2025