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

244 papers, page 4 of 5

151. ICLR 2026Muon Outperforms Adam in Tail-End Associative Memory Learning
152. ICLR 2026MuonBP: Faster Muon via Block-Periodic Orthogonalization
153. ICLR 2026Nearly Space-Optimal Graph and Hypergraph Sparsification in Insertion-Only Data Streams
154. ICLR 2026Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
155. ICLR 2026Neural Collapse in Multi-Task Learning
156. ICLR 2026Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
157. ICLR 2026Neural Multi-Objective Combinatorial Optimization for Flexible Job Shop Scheduling Problems
158. ICLR 2026Never Saddle: Reparameterized Steepest Descent as Mirror Flow
159. ICLR 2026Newton Method Revisited: Global Convergence Rates up to $O(1/k^3)$ for Stepsize Schedules and Linesearch Procedures
160. ICLR 2026Non-Asymptotic Analysis of Efficiency in Conformalized Regression
161. ICLR 2026Non-Convex Federated Optimization under Cost-Aware Client Selection
162. ICLR 2026On Smoothness Bounds for Non-Clairvoyant Scheduling with Predictions
163. ICLR 2026On the $O(1/T)$ Convergence of Alternating Gradient Descent–Ascent in Bilinear Games
164. ICLR 2026On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
165. ICLR 2026On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
166. ICLR 2026On the Convergence Direction of Gradient Descent
167. ICLR 2026On the Convergence of Two-Layer Kolmogorov-Arnold Networks with First-Layer Training
168. ICLR 2026On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning
169. ICLR 2026On Universality of Deep Equivariant Networks
170. ICLR 2026Online Decision-Focused Learning
171. ICLR 2026Online Inventory Optimization in Non-Stationary Environment
172. ICLR 2026Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
173. ICLR 2026Operator Theory-Driven Autoformulation of MDPs for Control of Queueing Systems
174. ICLR 2026OR-PRM: A Process Reward Model for Algorithmic Problem in Operations Research
175. ICLR 2026Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
176. ICLR 2026Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
177. ICLR 2026Predictive Differential Training Guided by Training Dynamics
178. ICLR 2026Provably Accelerated Imaging with Restarted Inertia and Score-based Image Priors
179. ICLR 2026Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction
180. ICLR 2026PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
181. ICLR 2026Quasi-Equivariant Metanetworks
182. ICLR 2026RADAR: Learning to Route with Asymmetry-aware Distance Representations
183. ICLR 2026Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
184. ICLR 2026Reducing Contextual Stochastic Bilevel Optimization via Structured Function Approximation
185. ICLR 2026Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
186. ICLR 2026RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
187. ICLR 2026Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training
188. ICLR 2026Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
189. ICLR 2026Riemannian Federated Learning via Averaging Gradient Streams
190. ICLR 2026Riemannian Zeroth-Order Gradient Estimation with Structure-Preserving Metrics for Geodesically Incomplete Manifolds
191. ICLR 2026Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
192. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
193. ICLR 2026Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
194. ICLR 2026SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety
195. ICLR 2026Scalable Second-order Riemannian Optimization for $K$-means Clustering
196. ICLR 2026Scaling Direct Feedback Learning with Theoretical Guarantees
197. ICLR 2026Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling
198. ICLR 2026SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
199. ICLR 2026Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
200. ICLR 2026Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGD

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.