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 4 of 6

151. NeurIPS 2024Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
152. NeurIPS 2024Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
153. NeurIPS 2024Non-asymptotic Convergence of Training Transformers for Next-token Prediction
154. NeurIPS 2024Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
155. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
156. NeurIPS 2024On $f$-Divergence Principled Domain Adaptation: An Improved Framework
157. NeurIPS 2024On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
158. NeurIPS 2024On the Ability of Developers' Training Data Preservation of Learnware
159. NeurIPS 2024On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
160. NeurIPS 2024On the Computational Landscape of Replicable Learning
161. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
162. NeurIPS 2024On the Efficiency of ERM in Feature Learning
163. NeurIPS 2024On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
164. NeurIPS 2024On the Limitations of Fractal Dimension as a Measure of Generalization
165. NeurIPS 2024On the Power of Decision Trees in Auto-Regressive Language Modeling
166. NeurIPS 2024On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
167. NeurIPS 2024On the Role of Attention Masks and LayerNorm in Transformers
168. NeurIPS 2024On the Saturation Effects of Spectral Algorithms in Large Dimensions
169. NeurIPS 2024On the Sparsity of the Strong Lottery Ticket Hypothesis
170. NeurIPS 2024On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
171. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
172. NeurIPS 2024Online Consistency of the Nearest Neighbor Rule
173. NeurIPS 2024Online Weighted Paging with Unknown Weights
174. NeurIPS 2024Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
175. NeurIPS 2024Optimal Algorithms for Augmented Testing of Discrete Distributions
176. NeurIPS 2024Optimal Algorithms for Learning Partitions with Faulty Oracles
177. NeurIPS 2024Optimal deep learning of holomorphic operators between Banach spaces
178. NeurIPS 2024Optimal Hypothesis Selection in (Almost) Linear Time
179. NeurIPS 2024Optimal Parallelization of Boosting
180. NeurIPS 2024Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
181. NeurIPS 2024Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
182. NeurIPS 2024Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
183. NeurIPS 2024PAC-Bayes-Chernoff bounds for unbounded losses
184. NeurIPS 2024Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
185. NeurIPS 2024Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
186. NeurIPS 2024Prospective Learning: Learning for a Dynamic Future
187. NeurIPS 2024Provable Benefit of Cutout and CutMix for Feature Learning
188. NeurIPS 2024Provable Benefits of Complex Parameterizations for Structured State Space Models
189. NeurIPS 2024Provable Tempered Overfitting of Minimal Nets and Typical Nets
190. NeurIPS 2024Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
191. NeurIPS 2024Quantifying the Gain in Weak-to-Strong Generalization
192. NeurIPS 2024Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
193. NeurIPS 2024Randomized Truthful Auctions with Learning Agents
194. NeurIPS 2024Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
195. NeurIPS 2024Reciprocal Learning
196. NeurIPS 2024Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
197. NeurIPS 2024Reliable Learning of Halfspaces under Gaussian Marginals
198. NeurIPS 2024Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
199. NeurIPS 2024Replicable Uniformity Testing
200. NeurIPS 2024Rethinking 3D Convolution in $\ell_p$-norm Space

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.