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 6 of 12

251. ICLR 2026WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data
252. ICML 2026A Constrained Optimization Perspective of Unrolled Transformers
253. ICML 2026A Direct Second-Order Method for Solving Two-Player Zero-Sum Games
254. ICML 2026A Fully First-Order Layer for Differentiable Optimization
255. ICML 2026A General Framework for Dynamic Consistent Submodular Maximization
256. ICML 2026A Linearly Convergent Proximal Subgradient Algorithm for Sparse Portfolio Optimization with Transaction Cost
257. ICML 2026A Perturbation Approach to Unconstrained Linear Bandits
258. ICML 2026A Random Matrix Theory of Masked Self-Supervised Learning
259. ICML 2026A Theoretical Framework for Modular Learning of Robust Generative Models
260. ICML 2026A Tight Theory of Error Feedback Algorithms in Distributed Optimization
261. ICML 2026Accelerated and Stable Convergence with Anchored Generalized Optimistic Method
262. ICML 2026AD-BTS: Adaptive Dual-Branch Token Sparsification via Spatial Information Density
263. ICML 2026Adapting to Evolving Graphs: A Scalable Framework for Dynamic Coarsening
264. ICML 2026Adaptive Momentum and Nonlinear Damping for Neural Network Training
265. ICML 2026Adaptive Preconditioners Trigger Loss Spikes in Adam
266. ICML 2026Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
267. ICML 2026AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
268. ICML 2026All ERMs Can Fail in Stochastic Convex Optimization Lower Bounds in Linear Dimension
269. ICML 2026An Algebraic View of the Expressivity of Recurrent Language Models
270. ICML 2026An analytic theory of convolutional neural network inverse problems solvers
271. ICML 2026An Efficient Joint Learning Approach for Item Response Theory
272. ICML 2026An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
273. ICML 2026Approximate Equivariance via Projection-Based Regularisation
274. ICML 2026Approximation Theory for Lipschitz Continuous Transformers
275. ICML 2026Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
276. ICML 2026Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards
277. ICML 2026Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
278. ICML 2026Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
279. ICML 2026BAS: Bridging Adam and SignSGD for Memory-Efficient LLM Training
280. ICML 2026Beyond Binary: Continuous State Optimization with Graph-Structured Objectives
281. ICML 2026Beyond Prediction: Tail-Aware Scheduling for LLM Inference
282. ICML 2026Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
283. ICML 2026Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge
284. ICML 2026Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time
285. ICML 2026Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
286. ICML 2026CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization
287. ICML 2026CLASP: Online learning algorithms for Convex Losses And Squared Penalties
288. ICML 2026Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
289. ICML 2026Combinatorial Sparse PCA Beyond the Spiked Identity Model
290. ICML 2026Complexity of Decentralized Optimization with Mixed Affine Constraints
291. ICML 2026Consistency Deep Equilibrium Models
292. ICML 2026Continuous Variable Hamiltonian Learning at Heisenberg Limit via Displacement-Random Unitary Transformation
293. ICML 2026Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization
294. ICML 2026Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
295. ICML 2026Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
296. ICML 2026Correcting Overparameterization Effects in Fair Empirical Risk Minimization
297. ICML 2026DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers
298. ICML 2026Data Reconstruction: Identifiability and Optimization with Sample Splitting
299. ICML 2026Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
300. ICML 2026Decentralized Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower Bounds

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.