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 11 of 27

501. ICLR 2025Attention layers provably solve single-location regression
502. ICLR 2025Bandit Learning in Matching Markets with Indifference
503. ICLR 2025Bayesian Treatment of the Spectrum of the Empirical Kernel in (Sub)Linear-Width Neural Networks
504. ICLR 2025Benign Overfitting in Out-of-Distribution Generalization of Linear Models
505. ICLR 2025Binary Losses for Density Ratio Estimation
506. ICLR 2025Block Verification Accelerates Speculative Decoding
507. ICLR 2025Bounds on $L_p$ Errors in Density Ratio Estimation via $f$-Divergence Loss Functions
508. ICLR 2025Bridging the Gap Between f-divergences and Bayes Hilbert Spaces
509. ICLR 2025Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
510. ICLR 2025Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model
511. ICLR 2025Can One Modality Model Synergize Training of Other Modality Models?
512. ICLR 2025Chain-of-Thought Provably Enables Learning the (Otherwise) Unlearnable
513. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
514. ICLR 2025Computational Explorations of Total Variation Distance
515. ICLR 2025Compute-Optimal LLMs Provably Generalize Better with Scale
516. ICLR 2025Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation
517. ICLR 2025Connectome Mapping: Shape-Memory Network via Interpretation of Contextual Semantic Information
518. ICLR 2025Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
519. ICLR 2025Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees
520. ICLR 2025Decomposition Polyhedra of Piecewise Linear Functions
521. ICLR 2025Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
522. ICLR 2025Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
523. ICLR 2025Distribution-Specific Agnostic Conditional Classification With Halfspaces
524. ICLR 2025Divergence of Neural Tangent Kernel in Classification Problems
525. ICLR 2025Dynamic Assortment Selection and Pricing with Censored Preference Feedback
526. ICLR 2025Exact Community Recovery under Side Information: Optimality of Spectral Algorithms
527. ICLR 2025Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
528. ICLR 2025Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality
529. ICLR 2025Extending Mercer's expansion to indefinite and asymmetric kernels
530. ICLR 2025Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
531. ICLR 2025Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
532. ICLR 2025From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
533. ICLR 2025From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency
534. ICLR 2025Fundamental Limitations on Subquadratic Alternatives to Transformers
535. ICLR 2025Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power
536. ICLR 2025Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks
537. ICLR 2025Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging
538. ICLR 2025Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors
539. ICLR 2025Generalized Principal-Agent Problem with a Learning Agent
540. ICLR 2025Geometry of Lightning Self-Attention: Identifiability and Dimension
541. ICLR 2025Global Convergence in Neural ODEs: Impact of Activation Functions
542. ICLR 2025Grokking at the Edge of Numerical Stability
543. ICLR 2025How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
544. ICLR 2025How Feature Learning Can Improve Neural Scaling Laws
545. ICLR 2025How Gradient descent balances features: A dynamical analysis for two-layer neural networks
546. ICLR 2025How many samples are needed to train a deep neural network?
547. ICLR 2025How Much is Unseen Depends Chiefly on Information About the Seen
548. ICLR 2025Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions
549. ICLR 2025Improved Convergence Rate for Diffusion Probabilistic Models
550. ICLR 2025Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

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.