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

584 papers, page 5 of 12

201. ICLR 2026SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety
202. ICLR 2026Scalable Second-order Riemannian Optimization for $K$-means Clustering
203. ICLR 2026Scaling Direct Feedback Learning with Theoretical Guarantees
204. ICLR 2026Seesaw: Accelerating Training by Balancing Batch Size and Learning Rate Scheduling
205. ICLR 2026SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
206. ICLR 2026Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
207. ICLR 2026Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGD
208. ICLR 2026Sign-SGD via Parameter-Free Optimization
209. ICLR 2026Single-Loop Byzantine-Resilient Federated Bilevel Optimization
210. ICLR 2026Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis
211. ICLR 2026Soft Quality-Diversity Optimization
212. ICLR 2026Solving the 2-norm k-hyperplane clustering problem via multi-norm formulations
213. ICLR 2026Special Unitary Parameterized Estimators of Rotation
214. ICLR 2026Statistical Advantage of Softmax Attention: Insights from Single-Location Regression
215. ICLR 2026StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
216. ICLR 2026Stop Guessing: Choosing the Optimization-Consistent Uncertainty Measurement for Evidential Deep Learning
217. ICLR 2026Strong Correlations Induce Cause Only Predictions in Transformer Training
218. ICLR 2026Strongly Convex Sets in Riemannian Manifolds
219. ICLR 2026Sublinear Time Quantum Algorithm for Attention Approximation
220. ICLR 2026Submodular Function Minimization with Dueling Oracle
221. ICLR 2026SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
222. ICLR 2026SVD Provably Denoises Nearest Neighbor Data
223. ICLR 2026T-TAMER: Provably Taming Trade-offs in ML Serving
224. ICLR 2026Task-free Adaptive Meta Black-box Optimization
225. ICLR 2026The Effect of Attention Head Count on Transformer Approximation
226. ICLR 2026The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm
227. ICLR 2026The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
228. ICLR 2026The Power of Small Initialization in Noisy Low-Tubal-Rank Tensor Recovery
229. ICLR 2026Thompson Sampling via Fine-Tuning of LLMs
230. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
231. ICLR 2026Tighter Performance Theory of FedExProx
232. ICLR 2026Towards a Sharp Analysis of Learning Offline $f$-Divergence-Regularized Contextual Bandits
233. ICLR 2026Towards Dynamic Interleaving Optimizers
234. ICLR 2026Towards Efficient Constraint Handling in Neural Solvers for Routing Problems
235. ICLR 2026Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
236. ICLR 2026Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov Framework
237. ICLR 2026Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization
238. ICLR 2026Tractability via Low Dimensionality: The Parameterized Complexity of Training Quantized Neural Networks
239. ICLR 2026Training Dynamics Impact Post-Training Quantization Robustness
240. ICLR 2026Tuning the burn-in phase in training recurrent neural networks improves their performance
241. ICLR 2026TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
242. ICLR 2026Two (narrow) heads are better than (an arbitrarily wide) one
243. ICLR 2026Two-Layer Convolutional Autoencoders Trained on Normal Data Provably Detect Unseen Anomalies
244. ICLR 2026Unbiased Gradient Estimation for Event Binning via Functional Backpropagation
245. ICLR 2026Understanding and improving Shampoo and SOAP via Kullback-Leibler Minimization
246. ICLR 2026Unified Analyses for Hierarchical Federated Learning: Topology Selection under Data Heterogeneity
247. ICLR 2026Unlocking the Potential of Weighting Methods in Federated Learning Through Communication Compression
248. ICLR 2026Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
249. ICLR 2026ViTSP: A Vision Language Models Guided Framework for Large-Scale Traveling Salesman Problems
250. ICLR 2026Why Less is More (Sometimes): A Theory of Data Curation

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.