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

482 papers, page 3 of 10

101. ICLR 2026Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains
102. ICLR 2026Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity
103. ICLR 2026Multi-Armed Bandits with Minimum Aggregated Revenue Constraints
104. ICLR 2026Near Optimal Robust Federated Learning Against Data Poisoning Attack
105. ICLR 2026Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
106. ICLR 2026Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit
107. ICLR 2026Never Saddle: Reparameterized Steepest Descent as Mirror Flow
108. ICLR 2026Neyman-Pearson Classification under Both Null and Alternative Distributions Shift
109. ICLR 2026No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
110. ICLR 2026Non-Asymptotic Analysis of (Sticky) Track-and-Stop
111. ICLR 2026Nonparametric Contextual Online Bilateral Trade
112. ICLR 2026On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
113. ICLR 2026On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
114. ICLR 2026On the Convergence of Two-Layer Kolmogorov-Arnold Networks with First-Layer Training
115. ICLR 2026On the Interpolation Effect of Score Smoothing in Diffusion Models
116. ICLR 2026ON THE ROLE OF IMPLICIT REGULARIZATION OF STOCHASTIC GRADIENT DESCENT IN GROUP ROBUSTNESS
117. ICLR 2026On Universality of Deep Equivariant Networks
118. ICLR 2026Online Conformal Prediction with Adversarial Feedback via Regret Minimization
119. ICLR 2026Online Inventory Optimization in Non-Stationary Environment
120. ICLR 2026Online Learning and Equilibrium Computation with Ranking Feedback
121. ICLR 2026Online Prediction of Stochastic Sequences with High Probability Regret Bounds
122. ICLR 2026Online Rounding and Learning Augmented Algorithms for Facility Location
123. ICLR 2026Oracle-efficient Hybrid Learning with Constrained Adversaries
124. ICLR 2026Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory
125. ICLR 2026Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
126. ICLR 2026Personalized Collaborative Learning with Affinity-Based Variance Reduction
127. ICLR 2026Physics-informed learning under mixing: How physical knowledge speeds up learning
128. ICLR 2026Poly-attention: a general scheme for higher-order self-attention
129. ICLR 2026Polynomial Convergence of Riemannian Diffusion Models
130. ICLR 2026Predicting Kernel Regression Learning Curves from Only Raw Data Statistics
131. ICLR 2026Predictive Differential Training Guided by Training Dynamics
132. ICLR 2026Pretrain–Test Task Alignment Governs Generalization in In-Context Learning
133. ICLR 2026Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
134. ICLR 2026Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data
135. ICLR 2026Quantitative Bounds for Length Generalization in Transformers
136. ICLR 2026Quantum machine learning advantages beyond hardness of evaluation
137. ICLR 2026Quasi-Equivariant Metanetworks
138. ICLR 2026Random Spiking Neural Networks are Stable and Spectrally Simple
139. ICLR 2026Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
140. ICLR 2026Replicable Reinforcement Learning with Linear Function Approximation
141. ICLR 2026Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
142. ICLR 2026Residual Feature Integration is Sufficient to Prevent Negative Transfer
143. ICLR 2026Revenue Maximization Under Sequential Price Competition Via The Estimation Of $s$-Concave Demand Functions
144. ICLR 2026Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training
145. ICLR 2026Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
146. ICLR 2026ROC-n-reroll: How verifier imperfection affects test-time scaling
147. ICLR 2026Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
148. ICLR 2026Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
149. ICLR 2026Sample Complexity and Representation Ability of Test-time Scaling Paradigms
150. ICLR 2026Sampling Complexity of TD and PPO in RKHS

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.