Theory · statistics papers, 2023–2026

Key findings

• Theory · statistics went from 16 papers in 2023 to 57 in 2026, roughly 3.6x in three years.
• NeurIPS publishes the most Theory · statistics work: 58 papers from 2023 to 2026, 42% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 1 in 2023 to 28 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #5 by 2026 paper count; the fastest grower in the group, Theory · learning theory, is up 5.6x versus 3.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Asymptotic Anytime-Valid Inference for U-statistics
• ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
• ICLR 2026The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics
• NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
• ICML 2025Contextual Bandits for Unbounded Context Distributions
• ICLR 2025Improving Pretraining Data Using Perplexity Correlations
• CVPR 2025Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics
• NeurIPS 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
• ICML 2024Neural Networks Learn Statistics of Increasing Complexity
• ICLR 2024Kernelised Normalising Flows
• NeurIPS 2023Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics
• ICML 2023Fair Densities via Boosting the Sufficient Statistics of Exponential Families
• ICLR 2023Don’t fear the unlabelled: safe semi-supervised learning via debiasing
• NeurIPS 2026Computationally sufficient statistics for Ising models
• ICML 2026Adaptive Multiscale Binary Expansion Tests for Independence
• ICLR 2026Bayesian Influence Functions for Hessian-Free Data Attribution
• NeurIPS 2025Backward Conformal Prediction
• ICML 2025Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
• ICLR 2025From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
• NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front

All Theory · statistics papers

58 papers, page 1 of 2

1. NeurIPS 2026Asymptotic Anytime-Valid Inference for U-statistics
2. NeurIPS 2026Computationally sufficient statistics for Ising models
3. NeurIPS 2026Hierarchical Concept Geometry in Language Representations Emerges from Word Co-occurrence
4. NeurIPS 2026Neural population tuning statistics as priors for multitask generalization
5. NeurIPS 2026Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models
6. NeurIPS 2026Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures
7. NeurIPS 2026Rare-Tail Statistics For Learning Biased Gaussian Halfspaces with Label Noise
8. NeurIPS 2026Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
9. NeurIPS 2026Symmetry Guarantees Statistic Recovery in Variational Inference
10. NeurIPS 2026TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
11. NeurIPS 2026What Transformer FFNs Never See: Theory, Diagnosis, and Lightweight Remediation
12. NeurIPS 2026Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics
13. NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
14. NeurIPS 2025Backward Conformal Prediction
15. NeurIPS 2025Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
16. NeurIPS 2025Co-Regularization Enhances Knowledge Transfer in High Dimensions
17. NeurIPS 2025Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
18. NeurIPS 2025Demystifying Spectral Feature Learning for Instrumental Variable Regression
19. NeurIPS 2025Estimation of Stochastic Optimal Transport Maps
20. NeurIPS 2025Improved Robust Estimation for Erdős-Rényi Graphs: The Sparse Regime and Optimal Breakdown Point
21. NeurIPS 2025Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination
22. NeurIPS 2025Integral Imprecise Probability Metrics
23. NeurIPS 2025Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation
24. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
25. NeurIPS 2025Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
26. NeurIPS 2025Private Statistical Estimation via Truncation
27. NeurIPS 2025Product Distribution Learning with Imperfect Advice
28. NeurIPS 2025Robust Estimation Under Heterogeneous Corruption Rates
29. NeurIPS 2025Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators
30. NeurIPS 2025STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals
31. NeurIPS 2025Statistical Inference for Gradient Boosting Regression
32. NeurIPS 2025Statistical Inference under Performativity
33. NeurIPS 2025Stochastic Gradients under Nuisances
34. NeurIPS 2025The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
35. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
36. NeurIPS 2024A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
37. NeurIPS 2024Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
38. NeurIPS 2024Bayes-optimal learning of an extensive-width neural network from quadratically many samples
39. NeurIPS 2024Breaking the curse of dimensionality in structured density estimation
40. NeurIPS 2024Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
41. NeurIPS 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
42. NeurIPS 2024Least Squares Regression Can Exhibit Under-Parameterized Double Descent
43. NeurIPS 2024On Differentially Private U Statistics
44. NeurIPS 2024On the Saturation Effects of Spectral Algorithms in Large Dimensions
45. NeurIPS 2024Optimal Hypothesis Selection in (Almost) Linear Time
46. NeurIPS 2024Robust Mixture Learning when Outliers Overwhelm Small Groups
47. NeurIPS 2024Scalable DBSCAN with Random Projections
48. NeurIPS 2024Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
49. NeurIPS 2024Statistical Multicriteria Benchmarking via the GSD-Front
50. NeurIPS 2023Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics

FAQ

How many Theory · statistics papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

138 in total: 16 in 2023, 21 in 2024, 44 in 2025, 57 in 2026.

How many Theory · statistics papers are at NeurIPS 2026?

NeurIPS 2026 has 12 Theory · statistics papers, versus 23 the year before.

How many Theory · statistics papers are at ICLR 2026?

ICLR 2026 has 15 Theory · statistics papers, versus 7 the year before.

How many Theory · statistics papers are at ICML 2026?

ICML 2026 has 30 Theory · statistics papers, versus 13 the year before.

How many Theory · statistics papers are at CVPR 2025?

CVPR 2025 has 1 Theory · statistics papers.

Which conference publishes the most Theory · statistics papers?

NeurIPS, with 58 papers from 2023 to 2026.