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 25 of 27

1201. NeurIPS 2024Robust Sparse Regression with Non-Isotropic Designs
1202. NeurIPS 2024Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
1203. NeurIPS 2024Sample-Efficient Agnostic Boosting
1204. NeurIPS 2024Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
1205. NeurIPS 2024Scaling laws for learning with real and surrogate data
1206. NeurIPS 2024Scaling Laws in Linear Regression: Compute, Parameters, and Data
1207. NeurIPS 2024Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
1208. NeurIPS 2024Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
1209. NeurIPS 2024Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
1210. NeurIPS 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
1211. NeurIPS 2024Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
1212. NeurIPS 2024Soft ascent-descent as a stable and flexible alternative to flooding
1213. NeurIPS 2024Solving Sparse \& High-Dimensional-Output Regression via Compression
1214. NeurIPS 2024Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
1215. NeurIPS 2024Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
1216. NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front
1217. NeurIPS 2024Statistical-Computational Trade-offs for Density Estimation
1218. NeurIPS 2024Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
1219. NeurIPS 2024Supervised Kernel Thinning
1220. NeurIPS 2024Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
1221. NeurIPS 2024Symmetric Linear Bandits with Hidden Symmetry
1222. NeurIPS 2024Testably Learning Polynomial Threshold Functions
1223. NeurIPS 2024The Benefits of Balance: From Information Projections to Variance Reduction
1224. NeurIPS 2024The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
1225. NeurIPS 2024The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
1226. NeurIPS 2024The Implicit Bias of Gradient Descent on Separable Multiclass Data
1227. NeurIPS 2024The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
1228. NeurIPS 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
1229. NeurIPS 2024The Many Faces of Optimal Weak-to-Strong Learning
1230. NeurIPS 2024The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
1231. NeurIPS 2024The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
1232. NeurIPS 2024The Power of Resets in Online Reinforcement Learning
1233. NeurIPS 2024The Price of Implicit Bias in Adversarially Robust Generalization
1234. NeurIPS 2024The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
1235. NeurIPS 2024The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
1236. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
1237. NeurIPS 2024Tight Bounds for Learning RUMs from Small Slates
1238. NeurIPS 2024Tolerant Algorithms for Learning with Arbitrary Covariate Shift
1239. NeurIPS 2024Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
1240. NeurIPS 2024Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
1241. NeurIPS 2024Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
1242. NeurIPS 2024Towards a theory of how the structure of language is acquired by deep neural networks
1243. NeurIPS 2024Towards the Dynamics of a DNN Learning Symbolic Interactions
1244. NeurIPS 2024Trade-Offs of Diagonal Fisher Information Matrix Estimators
1245. NeurIPS 2024Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
1246. NeurIPS 2024Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
1247. NeurIPS 2024Transductive Learning is Compact
1248. NeurIPS 2024Transfer Learning for Latent Variable Network Models
1249. NeurIPS 2024Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
1250. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners

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.