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

393 papers, page 6 of 8

251. NeurIPS 2024Learning from Snapshots of Discrete and Continuous Data Streams
252. NeurIPS 2024Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
253. NeurIPS 2024Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
254. NeurIPS 2024Learning Partitions from Context
255. NeurIPS 2024Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
256. NeurIPS 2024Learning the Infinitesimal Generator of Stochastic Diffusion Processes
257. NeurIPS 2024Learning via Surrogate PAC-Bayes
258. NeurIPS 2024Learning-Augmented Algorithms with Explicit Predictors
259. NeurIPS 2024Least Squares Regression Can Exhibit Under-Parameterized Double Descent
260. NeurIPS 2024Length Optimization in Conformal Prediction
261. NeurIPS 2024Linear Regression using Heterogeneous Data Batches
262. NeurIPS 2024Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
263. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
264. NeurIPS 2024Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
265. NeurIPS 2024Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
266. NeurIPS 2024Metric Transforms and Low Rank Representations of Kernels for Fast Attention
267. NeurIPS 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
268. NeurIPS 2024Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
269. NeurIPS 2024Model Collapse Demystified: The Case of Regression
270. NeurIPS 2024Multi-Label Learning with Stronger Consistency Guarantees
271. NeurIPS 2024Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
272. NeurIPS 2024Nature-Inspired Local Propagation
273. NeurIPS 2024Near-Optimality of Contrastive Divergence Algorithms
274. NeurIPS 2024Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
275. NeurIPS 2024Neural Collapse To Multiple Centers For Imbalanced Data
276. NeurIPS 2024Neural Conditional Probability for Uncertainty Quantification
277. NeurIPS 2024Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
278. NeurIPS 2024NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
279. NeurIPS 2024Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
280. NeurIPS 2024Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
281. NeurIPS 2024Non-asymptotic Convergence of Training Transformers for Next-token Prediction
282. NeurIPS 2024Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
283. NeurIPS 2024Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
284. NeurIPS 2024On $f$-Divergence Principled Domain Adaptation: An Improved Framework
285. NeurIPS 2024On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
286. NeurIPS 2024On the Ability of Developers' Training Data Preservation of Learnware
287. NeurIPS 2024On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
288. NeurIPS 2024On the Computational Landscape of Replicable Learning
289. NeurIPS 2024On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
290. NeurIPS 2024On the Efficiency of ERM in Feature Learning
291. NeurIPS 2024On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
292. NeurIPS 2024On the Limitations of Fractal Dimension as a Measure of Generalization
293. NeurIPS 2024On the Power of Decision Trees in Auto-Regressive Language Modeling
294. NeurIPS 2024On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
295. NeurIPS 2024On the Role of Attention Masks and LayerNorm in Transformers
296. NeurIPS 2024On the Saturation Effects of Spectral Algorithms in Large Dimensions
297. NeurIPS 2024On the Sparsity of the Strong Lottery Ticket Hypothesis
298. NeurIPS 2024On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
299. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
300. NeurIPS 2024Online Consistency of the Nearest Neighbor Rule

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.