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

540 papers, page 10 of 11

451. NeurIPS 2024The Power of Resets in Online Reinforcement Learning
452. NeurIPS 2024The Price of Implicit Bias in Adversarially Robust Generalization
453. NeurIPS 2024The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
454. NeurIPS 2024The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
455. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
456. NeurIPS 2024Tight Bounds for Learning RUMs from Small Slates
457. NeurIPS 2024Tolerant Algorithms for Learning with Arbitrary Covariate Shift
458. NeurIPS 2024Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
459. NeurIPS 2024Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
460. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
461. NeurIPS 2024Towards a theory of how the structure of language is acquired by deep neural networks
462. NeurIPS 2024Towards the Dynamics of a DNN Learning Symbolic Interactions
463. NeurIPS 2024Trade-Offs of Diagonal Fisher Information Matrix Estimators
464. NeurIPS 2024Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
465. NeurIPS 2024Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
466. NeurIPS 2024Transductive Learning is Compact
467. NeurIPS 2024Transfer Learning for Latent Variable Network Models
468. NeurIPS 2024Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
469. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners
470. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
471. NeurIPS 2024Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
472. NeurIPS 2024Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
473. NeurIPS 2024Understanding the Gains from Repeated Self-Distillation
474. NeurIPS 2024Understanding the Role of Equivariance in Self-supervised Learning
475. NeurIPS 2024Universal Rates for Active Learning
476. NeurIPS 2024Universal Rates of Empirical Risk Minimization
477. NeurIPS 2024Universality in Transfer Learning for Linear Models
478. NeurIPS 2024Unravelling in Collaborative Learning
479. NeurIPS 2024Unrolled denoising networks provably learn to perform optimal Bayesian inference
480. NeurIPS 2024Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
481. NeurIPS 2024Variance estimation in compound decision theory under boundedness
482. NeurIPS 2024Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
483. NeurIPS 2024Wide Two-Layer Networks can Learn from Adversarial Perturbations
484. NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
485. NeurIPS 2023A Measure-Theoretic Axiomatisation of Causality
486. NeurIPS 2023A Theory of Multimodal Learning
487. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
488. NeurIPS 2023Accelerating Value Iteration with Anchoring
489. NeurIPS 2023Agnostic Multi-Group Active Learning
490. NeurIPS 2023Alternation makes the adversary weaker in two-player games
491. NeurIPS 2023Bandit Social Learning under Myopic Behavior
492. NeurIPS 2023Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
493. NeurIPS 2023Bridging RL Theory and Practice with the Effective Horizon
494. NeurIPS 2023Characterization of Overfitting in Robust Multiclass Classification
495. NeurIPS 2023Common Ground in Cooperative Communication
496. NeurIPS 2023Delegated Classification
497. NeurIPS 2023Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback
498. NeurIPS 2023Equivariant Neural Operator Learning with Graphon Convolution
499. NeurIPS 2023Estimating the Rate-Distortion Function by Wasserstein Gradient Descent
500. NeurIPS 2023Faster Relative Entropy Coding with Greedy Rejection Coding

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.