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 10 of 27

451. NeurIPS 2026Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
452. NeurIPS 2026Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
453. NeurIPS 2026Post-Processing Guarantees for Classification under Linear-Fractional Performance Metrics
454. NeurIPS 2026Prediction Under Imperfect Compression: A Theory of Approximate MDL
455. NeurIPS 2026Propagation of Chaos in Contextual Flow Maps
456. NeurIPS 2026Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
457. NeurIPS 2026Regret Minimization in Single-Dimensional Contract-Design with Binary Actions
458. NeurIPS 2026Replicable Constrained Bandits
459. NeurIPS 2026Resolving AdaBoost Cycling with LLMs: A Computer-Assisted Counterexample
460. NeurIPS 2026Robust Statistical Estimators with Bounded Empirical Sensitivity
461. NeurIPS 2026Safe Linear Bandits with Unknown Safety Gaps
462. NeurIPS 2026SAMPPO: Structure-Aware Mirror Proximal Policy Optimization
463. NeurIPS 2026Second-Order Complexity Theory for Neural Networks
464. NeurIPS 2026Selling Information While Being an Interested Party
465. NeurIPS 2026Sharp Non-Asymptotic Analysis of the Penalized Challenger in $\beta$-EB-TCI for Bernoulli Bandits
466. NeurIPS 2026Testable and Actionable Calibration for Full Swap Regret
467. NeurIPS 2026The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction
468. NeurIPS 2026The Symmetries of Three-Layer ReLU Networks
469. NeurIPS 2026Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
470. NeurIPS 2026Theory on Attention Dynamics for Out-of-Distribution In-Context Learning
471. NeurIPS 2026Tight Generalization Bounds for Noiseless Inverse Optimization
472. NeurIPS 2026Topic-Aware Contextual Cascading Bandits
473. NeurIPS 2026Toward a theory of Evaluability
474. NeurIPS 2026Training-free Spatially Grounded Geometric Shape Encoding
475. NeurIPS 2026Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
476. NeurIPS 2026Understanding Generalization Requires Universal Induction
477. NeurIPS 2026Understanding Randomization in Greedy Model Search
478. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
479. NeurIPS 2026Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees
480. NeurIPS 2026Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
481. NeurIPS 2026When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers
482. NeurIPS 2026When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
483. CVPR 2025A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains
484. CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
485. CVPR 2025EvOcc: Accurate Semantic Occupancy for Automated Driving Using Evidence Theory
486. CVPR 2025Foundations of the Theory of Performance-Based Ranking
487. ICLR 2025A Solvable Attention for Neural Scaling Laws
488. ICLR 2025A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
489. ICLR 2025A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops
490. ICLR 2025A Theory of Initialisation's Impact on Specialisation
491. ICLR 2025A Unified Theory of Quantum Neural Network Loss Landscapes
492. ICLR 2025Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards
493. ICLR 2025Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
494. ICLR 2025Algorithmic Stability Based Generalization Bounds for Adversarial Training
495. ICLR 2025Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
496. ICLR 2025An Online Learning Theory of Trading-Volume Maximization
497. ICLR 2025Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra
498. ICLR 2025Ask, and it shall be given: On the Turing completeness of prompting
499. ICLR 2025Associative memory and dead neurons
500. ICLR 2025Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure

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.