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

670 papers, page 6 of 14

251. ICML 2025Extreme Value Policy Optimization for Safe Reinforcement Learning
252. ICML 2025Fast Tensor Completion via Approximate Richardson Iteration
253. ICML 2025Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
254. ICML 2025Features are fate: a theory of transfer learning in high-dimensional regression
255. ICML 2025FedECADO: A Dynamical System Model of Federated Learning
256. ICML 2025Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness
257. ICML 2025Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
258. ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
259. ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
260. ICML 2025General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization
261. ICML 2025Generalization of noisy SGD in unbounded non-convex settings
262. ICML 2025Generalization Performance of Ensemble Clustering: From Theory to Algorithm
263. ICML 2025Generalized additive models via direct optimization of regularized decision stump forests
264. ICML 2025Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level
265. ICML 2025Global curvature for second-order optimization of neural networks
266. ICML 2025Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs
267. ICML 2025Graph-Based Algorithms for Diverse Similarity Search
268. ICML 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
269. ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
270. ICML 2025High-Dimensional Prediction for Sequential Decision Making
271. ICML 2025Identifying Metric Structures of Deep Latent Variable Models
272. ICML 2025Improved Approximations for Hard Graph Problems using Predictions
273. ICML 2025Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
274. ICML 2025Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
275. ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
276. ICML 2025Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
277. ICML 2025Inverse Optimization via Learning Feasible Regions
278. ICML 2025Joint Learning of Energy-based Models and their Partition Function
279. ICML 2025Joker: Joint Optimization Framework for Lightweight Kernel Machines
280. ICML 2025Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
281. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
282. ICML 2025Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
283. ICML 2025Learning Mixtures of Experts with EM: A Mirror Descent Perspective
284. ICML 2025Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems
285. ICML 2025Learning with Exact Invariances in Polynomial Time
286. ICML 2025Learning-Augmented Hierarchical Clustering
287. ICML 2025LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
288. ICML 2025Loss Functions and Operators Generated by f-Divergences
289. ICML 2025MARS: Unleashing the Power of Variance Reduction for Training Large Models
290. ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
291. ICML 2025Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
292. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
293. ICML 2025Modular Duality in Deep Learning
294. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
295. ICML 2025Multiobjective distribution matching
296. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
297. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
298. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
299. ICML 2025On Differential Privacy for Adaptively Solving Search Problems via Sketching
300. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning

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.