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

1,350 papers, page 4 of 27

151. ICLR 2026Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
152. ICLR 2026Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
153. ICLR 2026Semi-Parametric Contextual Pricing with General Smoothness
154. ICLR 2026Sequences of Logits Reveal the Low Rank Structure of Language Models
155. ICLR 2026SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines
156. ICLR 2026Sharp asymptotic theory for Q-learning with \texttt{LD2Z} learning rate and its generalization
157. ICLR 2026Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions
158. ICLR 2026Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis
159. ICLR 2026Stable coresets: Unleashing the power of uniform sampling
160. ICLR 2026Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
161. ICLR 2026Sublinear Spectral Clustering Oracle with Little Memory
162. ICLR 2026Subquadratic Algorithms and Hardness for Attention with Any Temperature
163. ICLR 2026SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
164. ICLR 2026Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
165. ICLR 2026The Coverage Principle: How Pre-Training Enables Post-Training
166. ICLR 2026The Effect of Attention Head Count on Transformer Approximation
167. ICLR 2026The Expressive Limits of Diagonal SSMs for State-Tracking
168. ICLR 2026The Price of Robustness: Stable Classifiers Need Overparameterization
169. ICLR 2026The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective
170. ICLR 2026The Serial Scaling Hypothesis
171. ICLR 2026Theoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution
172. ICLR 2026Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
173. ICLR 2026Tight Bounds for Schrodinger Potential Estimation in Unpaired Data Translation
174. ICLR 2026Tighter Performance Theory of FedExProx
175. ICLR 2026Topology and geometry of the learning space of ReLU networks: connectivity and singularities
176. ICLR 2026Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connections
177. ICLR 2026Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual Bandits
178. ICLR 2026Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D Generalisation
179. ICLR 2026Towards a Universally Transferable Acceleration Method for Density Functional Theory
180. ICLR 2026Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks
181. ICLR 2026Training-Free Determination of Network Width via Neural Tangent Kernel
182. ICLR 2026Transfer Learning in Infinite Width Feature Learning Networks
183. ICLR 2026Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
184. ICLR 2026Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures
185. ICLR 2026Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
186. ICLR 2026Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation
187. ICLR 2026Tuning the burn-in phase in training recurrent neural networks improves their performance
188. ICLR 2026Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
189. ICLR 2026Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen Anomalies
190. ICLR 2026Unbiased Gradient Estimation for Event Binning via Functional Backpropagation
191. ICLR 2026Understanding the Dynamics of Forgetting and Generalization in Continual Learning via the Neural Tangent Kernel
192. ICLR 2026Understanding the Role of Training Data in Test-Time Scaling
193. ICLR 2026Variational Inference for Cyclic Learning
194. ICLR 2026Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
195. ICLR 2026When Bias Helps Learning: Bridging Initial Prejudice and Trainability
196. ICLR 2026When Flatness Does (Not) Guarantee Adversarial Robustness
197. ICLR 2026When Is Diversity Rewarded in Cooperative Multi-Agent Learning?
198. ICLR 2026Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
199. ICLR 2026Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
200. ICLR 2026Why Less is More (Sometimes): A Theory of Data Curation

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.