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 9 of 11

401. NeurIPS 2024PAC-Bayes-Chernoff bounds for unbounded losses
402. NeurIPS 2024Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
403. NeurIPS 2024Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
404. NeurIPS 2024Prospective Learning: Learning for a Dynamic Future
405. NeurIPS 2024Provable Benefit of Cutout and CutMix for Feature Learning
406. NeurIPS 2024Provable Benefits of Complex Parameterizations for Structured State Space Models
407. NeurIPS 2024Provable Tempered Overfitting of Minimal Nets and Typical Nets
408. NeurIPS 2024Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
409. NeurIPS 2024Quantifying the Gain in Weak-to-Strong Generalization
410. NeurIPS 2024Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
411. NeurIPS 2024Randomized Truthful Auctions with Learning Agents
412. NeurIPS 2024Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
413. NeurIPS 2024Reciprocal Learning
414. NeurIPS 2024Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
415. NeurIPS 2024Reliable Learning of Halfspaces under Gaussian Marginals
416. NeurIPS 2024Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
417. NeurIPS 2024Replicable Uniformity Testing
418. NeurIPS 2024Rethinking 3D Convolution in $\ell_p$-norm Space
419. NeurIPS 2024Robust Mixture Learning when Outliers Overwhelm Small Groups
420. NeurIPS 2024Robust Sparse Regression with Non-Isotropic Designs
421. NeurIPS 2024Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
422. NeurIPS 2024Sample-Efficient Agnostic Boosting
423. NeurIPS 2024Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
424. NeurIPS 2024Scaling laws for learning with real and surrogate data
425. NeurIPS 2024Scaling Laws in Linear Regression: Compute, Parameters, and Data
426. NeurIPS 2024Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
427. NeurIPS 2024Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
428. NeurIPS 2024Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
429. NeurIPS 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
430. NeurIPS 2024Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
431. NeurIPS 2024Soft ascent-descent as a stable and flexible alternative to flooding
432. NeurIPS 2024Solving Sparse \& High-Dimensional-Output Regression via Compression
433. NeurIPS 2024Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
434. NeurIPS 2024Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
435. NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front
436. NeurIPS 2024Statistical-Computational Trade-offs for Density Estimation
437. NeurIPS 2024Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
438. NeurIPS 2024Supervised Kernel Thinning
439. NeurIPS 2024Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
440. NeurIPS 2024Symmetric Linear Bandits with Hidden Symmetry
441. NeurIPS 2024Testably Learning Polynomial Threshold Functions
442. NeurIPS 2024The Benefits of Balance: From Information Projections to Variance Reduction
443. NeurIPS 2024The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
444. NeurIPS 2024The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
445. NeurIPS 2024The Implicit Bias of Gradient Descent on Separable Multiclass Data
446. NeurIPS 2024The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
447. NeurIPS 2024The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
448. NeurIPS 2024The Many Faces of Optimal Weak-to-Strong Learning
449. NeurIPS 2024The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
450. NeurIPS 2024The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective

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.