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

540 papers, page 7 of 11

301. NeurIPS 2024Generalized Eigenvalue Problems with Generative Priors
302. NeurIPS 2024Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
303. NeurIPS 2024Generative Forests
304. NeurIPS 2024Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
305. NeurIPS 2024Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
306. NeurIPS 2024Group-wise oracle-efficient algorithms for online multi-group learning
307. NeurIPS 2024Hardness of Learning Neural Networks under the Manifold Hypothesis
308. NeurIPS 2024Harnessing Multiple Correlated Networks for Exact Community Recovery
309. NeurIPS 2024High-dimensional (Group) Adversarial Training in Linear Regression
310. NeurIPS 2024How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
311. NeurIPS 2024How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
312. NeurIPS 2024How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
313. NeurIPS 2024How many classifiers do we need?
314. NeurIPS 2024How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
315. NeurIPS 2024How to Boost Any Loss Function
316. NeurIPS 2024How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
317. NeurIPS 2024Hyperbolic Embeddings of Supervised Models
318. NeurIPS 2024Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
319. NeurIPS 2024Implicit Regularization Paths of Weighted Neural Representations
320. NeurIPS 2024Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
321. NeurIPS 2024Improved Sample Complexity Bounds for Diffusion Model Training
322. NeurIPS 2024Improved Sample Complexity for Multiclass PAC Learning
323. NeurIPS 2024Improving Adaptivity via Over-Parameterization in Sequence Models
324. NeurIPS 2024Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
325. NeurIPS 2024In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
326. NeurIPS 2024In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
327. NeurIPS 2024Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
328. NeurIPS 2024Information-theoretic Generalization Analysis for Expected Calibration Error
329. NeurIPS 2024Information-theoretic Limits of Online Classification with Noisy Labels
330. NeurIPS 2024Invariant subspaces and PCA in nearly matrix multiplication time
331. NeurIPS 2024Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
332. NeurIPS 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
333. NeurIPS 2024Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance?
334. NeurIPS 2024Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
335. NeurIPS 2024Label Noise: Ignorance Is Bliss
336. NeurIPS 2024Language Generation in the Limit
337. NeurIPS 2024Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
338. NeurIPS 2024Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
339. NeurIPS 2024Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
340. NeurIPS 2024Learning from Noisy Labels via Conditional Distributionally Robust Optimization
341. NeurIPS 2024Learning from Snapshots of Discrete and Continuous Data Streams
342. NeurIPS 2024Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
343. NeurIPS 2024Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
344. NeurIPS 2024Learning Partitions from Context
345. NeurIPS 2024Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
346. NeurIPS 2024Learning the Infinitesimal Generator of Stochastic Diffusion Processes
347. NeurIPS 2024Learning via Surrogate PAC-Bayes
348. NeurIPS 2024Learning-Augmented Algorithms with Explicit Predictors
349. NeurIPS 2024Least Squares Regression Can Exhibit Under-Parameterized Double Descent
350. NeurIPS 2024Length Optimization in Conformal Prediction

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.