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

778 papers, page 5 of 16

201. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
202. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
203. NeurIPS 2025Effective Neural Approximations for Geometric Optimization Problems
204. NeurIPS 2025Efficient Adaptive Federated Optimization
205. NeurIPS 2025Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
206. NeurIPS 2025Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
207. NeurIPS 2025Efficient Quadratic Corrections for Frank-Wolfe Algorithms
208. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
209. NeurIPS 2025Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
210. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
211. NeurIPS 2025Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
212. NeurIPS 2025Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
213. NeurIPS 2025Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation
214. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
215. NeurIPS 2025Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
216. NeurIPS 2025Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
217. NeurIPS 2025Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
218. NeurIPS 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
219. NeurIPS 2025Exploring Landscapes for Better Minima along Valleys
220. NeurIPS 2025Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
221. NeurIPS 2025Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
222. NeurIPS 2025Fairness-Regularized Online Optimization with Switching Costs
223. NeurIPS 2025Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
224. NeurIPS 2025Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
225. NeurIPS 2025Fast Zeroth-Order Convex Optimization with Quantum Gradient Methods
226. NeurIPS 2025Faster Algorithms for Structured John Ellipsoid Computation
227. NeurIPS 2025Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints
228. NeurIPS 2025Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW
229. NeurIPS 2025Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds
230. NeurIPS 2025Flat Channels to Infinity in Neural Loss Landscapes
231. NeurIPS 2025Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
232. NeurIPS 2025Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
233. NeurIPS 2025FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
234. NeurIPS 2025FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization
235. NeurIPS 2025FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
236. NeurIPS 2025Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent
237. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
238. NeurIPS 2025Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming
239. NeurIPS 2025Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
240. NeurIPS 2025GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
241. NeurIPS 2025Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks
242. NeurIPS 2025Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies
243. NeurIPS 2025Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
244. NeurIPS 2025Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
245. NeurIPS 2025Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions
246. NeurIPS 2025Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
247. NeurIPS 2025HEIR: Learning Graph-Based Motion Hierarchies
248. NeurIPS 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
249. NeurIPS 2025Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
250. NeurIPS 2025Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints

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.