Theory · optimization papers, 2023–2026

Key findings

• Theory · optimization went from 123 papers in 2023 to 584 in 2026, roughly 4.7x in three years.
• NeurIPS publishes the most Theory · optimization work: 778 papers from 2023 to 2026, 42% of the four-venue total.
• The fastest-growing overlap is with Low-Rank Adaptation: papers tagged with both rose from 0 in 2023 to 31 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #1 by 2026 paper count; the fastest grower in the group, Theory · learning theory, is up 5.6x versus 4.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
• ICML 2026A Direct Second-Order Method for Solving Two-Player Zero-Sum Games
• ICLR 2026A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
• CVPR 2026TriSim Tri-Dimensional Similarity Modeling with Extreme Value Theory for False-Negative
• NeurIPS 20253BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
• ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
• ICLR 2025A Coefficient Makes SVRG Effective
• CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
• NeurIPS 2024A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
• ICML 2024A Statistical Theory of Regularization-Based Continual Learning
• ICLR 2024A Discretization Framework for Robust Contextual Stochastic Optimization
• NeurIPS 2023[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
• ICML 2023Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity
• ICLR 2023Adaptive Optimization in the $\infty$-Width Limit
• CVPR 2023Deep Hashing With Minimal-Distance-Separated Hash Centers
• NeurIPS 2026Avoiding Obfuscation with Prover-Estimator Debate
• ICML 2026A General Framework for Dynamic Consistent Submodular Maximization
• ICLR 2026A Memory-Efficient Hierarchical Algorithm for Large-scale Optimal Transport Problems
• CVPR 2026FedAdamom Adaptive Momentum for Improved Generalization in Federated Optimization
• NeurIPS 2025A Beyond-Worst-Case Analysis of Greedy k-means++

All Theory · optimization papers

196 papers, page 4 of 4

151. ICLR 2025qNBO: quasi-Newton Meets Bilevel Optimization
152. ICLR 2025Quality over Quantity in Attention Layers: When Adding More Heads Hurts
153. ICLR 2025Quantum (Inspired) $D^2$-sampling with Applications
154. ICLR 2025Rethinking Light Decoder-based Solvers for Vehicle Routing Problems
155. ICLR 2025Revisiting Large-Scale Non-convex Distributionally Robust Optimization
156. ICLR 2025Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
157. ICLR 2025Robustness of Quantum Algorithms for Nonconvex Optimization
158. ICLR 2025Scalable Decentralized Learning with Teleportation
159. ICLR 2025Scaling FP8 training to trillion-token LLMs
160. ICLR 2025Second-Order Min-Max Optimization with Lazy Hessians
161. ICLR 2025Self-Play Preference Optimization for Language Model Alignment
162. ICLR 2025SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
163. ICLR 2025Separation Power of Equivariant Neural Networks
164. ICLR 2025Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
165. ICLR 2025SGD with memory: fundamental properties and stochastic acceleration
166. ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
167. ICLR 2025Sharpness-Aware Black-Box Optimization
168. ICLR 2025Sharpness-Aware Minimization: General Analysis and Improved Rates
169. ICLR 2025SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling
170. ICLR 2025Solving hidden monotone variational inequalities with surrogate losses
171. ICLR 2025SOREL: A Stochastic Algorithm for Spectral Risks Minimization
172. ICLR 2025Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
173. ICLR 2025Strategic Classification With Externalities
174. ICLR 2025Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression
175. ICLR 2025Taming Transformer Without Using Learning Rate Warmup
176. ICLR 2025The Complexity of Two-Team Polymatrix Games with Independent Adversaries
177. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
178. ICLR 2025The Directionality of Optimization Trajectories in Neural Networks
179. ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
180. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
181. ICLR 2025Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
182. ICLR 2025Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics
183. ICLR 2025To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
184. ICLR 2025Towards Faster Decentralized Stochastic Optimization with Communication Compression
185. ICLR 2025Towards Foundation Models for Mixed Integer Linear Programming
186. ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
187. ICLR 2025Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
188. ICLR 2025Understanding Optimization in Deep Learning with Central Flows
189. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
190. ICLR 2025Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
191. ICLR 2025Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
192. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
193. ICLR 2025Vertical Federated Learning with Missing Features During Training and Inference
194. ICLR 2025What should a neuron aim for? Designing local objective functions based on information theory
195. ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
196. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

FAQ

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

1,871 in total: 123 in 2023, 494 in 2024, 670 in 2025, 584 in 2026.

How many Theory · optimization papers are at NeurIPS 2026?

NeurIPS 2026 has 119 Theory · optimization papers, versus 318 the year before.

How many Theory · optimization papers are at ICLR 2026?

ICLR 2026 has 244 Theory · optimization papers, versus 196 the year before.

How many Theory · optimization papers are at ICML 2026?

ICML 2026 has 214 Theory · optimization papers, versus 147 the year before.

How many Theory · optimization papers are at CVPR 2026?

CVPR 2026 has 7 Theory · optimization papers, versus 9 the year before.

Which conference publishes the most Theory · optimization papers?

NeurIPS, with 778 papers from 2023 to 2026.