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

265 papers, page 2 of 6

51. NeurIPS 2024Cryptographic Hardness of Score Estimation
52. NeurIPS 2024Data subsampling for Poisson regression with pth-root-link
53. NeurIPS 2024Derandomizing Multi-Distribution Learning
54. NeurIPS 2024Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
55. NeurIPS 2024Differentiable Quantum Computing for Large-scale Linear Control
56. NeurIPS 2024Dimension-free deterministic equivalents and scaling laws for random feature regression
57. NeurIPS 2024Distributed Least Squares in Small Space via Sketching and Bias Reduction
58. NeurIPS 2024Distribution Learning with Valid Outputs Beyond the Worst-Case
59. NeurIPS 2024Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
60. NeurIPS 2024Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
61. NeurIPS 2024Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
62. NeurIPS 2024ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
63. NeurIPS 2024Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
64. NeurIPS 2024Efficient Discrepancy Testing for Learning with Distribution Shift
65. NeurIPS 2024Efficient Graph Matching for Correlated Stochastic Block Models
66. NeurIPS 2024Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
67. NeurIPS 2024Entropy testing and its application to testing Bayesian networks
68. NeurIPS 2024Entrywise error bounds for low-rank approximations of kernel matrices
69. NeurIPS 2024Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
70. NeurIPS 2024Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
71. NeurIPS 2024Euclidean distance compression via deep random features
72. NeurIPS 2024Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
73. NeurIPS 2024Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
74. NeurIPS 2024Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
75. NeurIPS 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
76. NeurIPS 2024From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
77. NeurIPS 2024Generalizablity of Memorization Neural Network
78. NeurIPS 2024Generalization Analysis for Label-Specific Representation Learning
79. NeurIPS 2024Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
80. NeurIPS 2024Generalization Bounds via Conditional $f$-Information
81. NeurIPS 2024Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
82. NeurIPS 2024Generalization of Hamiltonian algorithms
83. NeurIPS 2024Generalized Eigenvalue Problems with Generative Priors
84. NeurIPS 2024Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
85. NeurIPS 2024Generative Forests
86. NeurIPS 2024Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
87. NeurIPS 2024Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
88. NeurIPS 2024Group-wise oracle-efficient algorithms for online multi-group learning
89. NeurIPS 2024Hardness of Learning Neural Networks under the Manifold Hypothesis
90. NeurIPS 2024Harnessing Multiple Correlated Networks for Exact Community Recovery
91. NeurIPS 2024High-dimensional (Group) Adversarial Training in Linear Regression
92. NeurIPS 2024How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
93. NeurIPS 2024How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
94. NeurIPS 2024How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
95. NeurIPS 2024How many classifiers do we need?
96. NeurIPS 2024How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
97. NeurIPS 2024How to Boost Any Loss Function
98. NeurIPS 2024How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
99. NeurIPS 2024Hyperbolic Embeddings of Supervised Models
100. NeurIPS 2024Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees

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.