Theory · learning theory papers, 2023–2026

Key findings

• Theory · learning theory went from 86 papers in 2023 to 482 in 2026, roughly 5.6x in three years.
• NeurIPS publishes the most Theory · learning theory work: 540 papers from 2023 to 2026, 40% of the four-venue total.
• The fastest-growing overlap is with Social aspects · accountability transparency and interpretability: papers tagged with both rose from 0 in 2023 to 33 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #2 by 2026 paper count; the fastest grower in the group, Theory · optimization, is up 4.7x versus 5.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A dynamical systems theory of reward-modulated learning in linear recurrent networks
• ICML 2026A Fine-Grained Understanding of Uniform Convergence for Halfspaces
• ICLR 2026A Law of Data Reconstruction for Random Features (And Beyond)
• NeurIPS 2025A Geometric Analysis of PCA
• ICML 2025A Generalization Theory for Zero-Shot Prediction
• ICLR 2025A Solvable Attention for Neural Scaling Laws
• CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
• NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
• ICML 2024A Statistical Theory of Regularization-Based Continual Learning
• ICLR 2024A Sublinear Adversarial Training Algorithm
• CVPR 2024Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Robust Collaborative Learning with Linear Gradient Overhead
• ICLR 2023Bispectral Neural Networks
• NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
• ICML 2026A Random Matrix Theory of Masked Self-Supervised Learning
• ICLR 2026A New Approach to Controlling Linear Dynamical Systems
• NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
• ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
• ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

All Theory · learning theory papers

1,350 papers, page 13 of 27

601. ICLR 2025Semialgebraic Neural Networks: From roots to representations
602. ICLR 2025Separation Power of Equivariant Neural Networks
603. ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
604. ICLR 2025Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees
605. ICLR 2025State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
606. ICLR 2025Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
607. ICLR 2025Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs
608. ICLR 2025Stochastic Bandits Robust to Adversarial Attacks
609. ICLR 2025Strong Model Collapse
610. ICLR 2025Task Descriptors Help Transformers Learn Linear Models In-Context
611. ICLR 2025The Breakdown of Gaussian Universality in Classification of High-dimensional Linear Factor Mixtures
612. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
613. ICLR 2025The Foundations of Tokenization: Statistical and Computational Concerns
614. ICLR 2025Theory on Mixture-of-Experts in Continual Learning
615. ICLR 2025Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
616. ICLR 2025Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization
617. ICLR 2025Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification
618. ICLR 2025Towards Understanding the Universality of Transformers for Next-Token Prediction
619. ICLR 2025Tractable Multi-Agent Reinforcement Learning through Behavioral Economics
620. ICLR 2025Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
621. ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
622. ICLR 2025Transformer Learns Optimal Variable Selection in Group-Sparse Classification
623. ICLR 2025Transformers are Universal In-context Learners
624. ICLR 2025Transformers Handle Endogeneity in In-Context Linear Regression
625. ICLR 2025Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought
626. ICLR 2025Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
627. ICLR 2025Transformers Provably Solve Parity Efficiently with Chain of Thought
628. ICLR 2025U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
629. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
630. ICLR 2025uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
631. ICLR 2025When does compositional structure yield compositional generalization? A kernel theory.
632. ICLR 2025When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
633. ICLR 2025When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
634. ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
635. ICML 2025A Generalization Theory for Zero-Shot Prediction
636. ICML 2025A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning
637. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
638. ICML 2025A Theory for Conditional Generative Modeling on Multiple Data Sources
639. ICML 2025A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
640. ICML 2025A Unified Framework for Generalization Error Analysis of Learning with Arbitrary Discrete Weak Features
641. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
642. ICML 2025A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
643. ICML 2025Adversarial Robust Generalization of Graph Neural Networks
644. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
645. ICML 2025Algorithms with Calibrated Machine Learning Predictions
646. ICML 2025All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance
647. ICML 2025An analytic theory of creativity in convolutional diffusion models
648. ICML 2025An Augmentation-Aware Theory for Self-Supervised Contrastive Learning
649. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
650. ICML 2025Anytime-Constrained Equilibria in Polynomial Time

FAQ

How many Theory · learning theory papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,350 in total: 86 in 2023, 393 in 2024, 389 in 2025, 482 in 2026.

How many Theory · learning theory papers are at NeurIPS 2026?

NeurIPS 2026 has 112 Theory · learning theory papers, versus 106 the year before.

How many Theory · learning theory papers are at ICLR 2026?

ICLR 2026 has 200 Theory · learning theory papers, versus 147 the year before.

How many Theory · learning theory papers are at ICML 2026?

ICML 2026 has 170 Theory · learning theory papers, versus 132 the year before.

How many Theory · learning theory papers are at CVPR 2025?

CVPR 2025 has 4 Theory · learning theory papers, versus 1 the year before.

Which conference publishes the most Theory · learning theory papers?

NeurIPS, with 540 papers from 2023 to 2026.