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 3 of 11

101. NeurIPS 2026Tight Generalization Bounds for Noiseless Inverse Optimization
102. NeurIPS 2026Topic-Aware Contextual Cascading Bandits
103. NeurIPS 2026Toward a theory of Evaluability
104. NeurIPS 2026Training-free Spatially Grounded Geometric Shape Encoding
105. NeurIPS 2026Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
106. NeurIPS 2026Understanding Generalization Requires Universal Induction
107. NeurIPS 2026Understanding Randomization in Greedy Model Search
108. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
109. NeurIPS 2026Universal Approximation Theorems for Dynamical Systems with Infinite-Time Horizon Guarantees
110. NeurIPS 2026Variance-Adaptive Optimal Algorithm for Reinforcement Learning with MNL Function Approximation
111. NeurIPS 2026When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers
112. NeurIPS 2026When Symbol Names Should Not Matter: A Logistic Theory of Fresh-Symbol Classification
113. NeurIPS 2025A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
114. NeurIPS 2025A Geometric Analysis of PCA
115. NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
116. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
117. NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
118. NeurIPS 2025A unified framework for establishing the universal approximation of transformer-type architectures
119. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
120. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
121. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
122. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
123. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
124. NeurIPS 2025Benign Overfitting in Single-Head Attention
125. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
126. NeurIPS 2025Beyond Benign Overfitting in Nadaraya-Watson Interpolators
127. NeurIPS 2025Block Coordinate Descent for Neural Networks Provably Finds Global Minima
128. NeurIPS 2025Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
129. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
130. NeurIPS 2025Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
131. NeurIPS 2025Computable universal online learning
132. NeurIPS 2025Computational Efficiency under Covariate Shift in Kernel Ridge Regression
133. NeurIPS 2025Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
134. NeurIPS 2025Constant Bit-size Transformers Are Turing Complete
135. NeurIPS 2025Constrained Linear Thompson Sampling
136. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
137. NeurIPS 2025Curl Descent : Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
138. NeurIPS 2025Cyclic Counterfactuals under Shift–Scale Interventions
139. NeurIPS 2025Disentangling Hyperedges through the Lens of Category Theory
140. NeurIPS 2025Distributional Training Data Attribution: What do Influence Functions Sample?
141. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
142. NeurIPS 2025Eluder dimension: localise it!
143. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
144. NeurIPS 2025Exact Expressive Power of Transformers with Padding
145. NeurIPS 2025Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training
146. NeurIPS 2025Fast attention mechanisms: a tale of parallelism
147. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
148. NeurIPS 2025How Particle System Theory Enhances Hypergraph Message Passing
149. NeurIPS 2025Identifiability of Deep Polynomial Neural Networks
150. NeurIPS 2025Improved Balanced Classification with Theoretically Grounded Loss Functions

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.