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 3 of 14

101. ICLR 2025Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability
102. ICLR 2025Learning Hierarchical Polynomials of Multiple Nonlinear Features
103. ICLR 2025Learning High-Degree Parities: The Crucial Role of the Initialization
104. ICLR 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
105. ICLR 2025Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
106. ICLR 2025Learning-Augmented Search Data Structures
107. ICLR 2025Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling
108. ICLR 2025Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
109. ICLR 2025Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
110. ICLR 2025Linear Partial Gromov-Wasserstein Embedding
111. ICLR 2025LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
112. ICLR 2025Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
113. ICLR 2025Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
114. ICLR 2025Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression
115. ICLR 2025LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
116. ICLR 2025LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
117. ICLR 2025Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
118. ICLR 2025Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
119. ICLR 2025Making Transformer Decoders Better Differentiable Indexers
120. ICLR 2025Mask in the Mirror: Implicit Sparsification
121. ICLR 2025MAST: model-agnostic sparsified training
122. ICLR 2025Matrix Product Sketching via Coordinated Sampling
123. ICLR 2025Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
124. ICLR 2025Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
125. ICLR 2025MGDA Converges under Generalized Smoothness, Provably
126. ICLR 2025Minimalistic Predictions for Online Class Constraint Scheduling
127. ICLR 2025MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
128. ICLR 2025Multi-objective Differentiable Neural Architecture Search
129. ICLR 2025Nesterov acceleration in benignly non-convex landscapes
130. ICLR 2025Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization
131. ICLR 2025New Algorithms for the Learning-Augmented k-means Problem
132. ICLR 2025Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
133. ICLR 2025Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State Sampling
134. ICLR 2025Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation
135. ICLR 2025Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
136. ICLR 2025OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference
137. ICLR 2025Offline Model-Based Optimization by Learning to Rank
138. ICLR 2025On Stochastic Contextual Bandits with Knapsacks in Small Budget Regime
139. ICLR 2025On the Almost Sure Convergence of the Stochastic Three Points Algorithm
140. ICLR 2025On the Crucial Role of Initialization for Matrix Factorization
141. ICLR 2025On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
142. ICLR 2025On the Optimal Memorization Capacity of Transformers
143. ICLR 2025On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
144. ICLR 2025On the Performance Analysis of Momentum Method: A Frequency Domain Perspective
145. ICLR 2025OPTAMI: Global Superlinear Convergence of High-order Methods
146. ICLR 2025Optimal Flow Transport and its Entropic Regularization: a GPU-friendly Matrix Iterative Algorithm for Flow Balance Satisfaction
147. ICLR 2025Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design
148. ICLR 2025Optimization by Parallel Quasi-Quantum Annealing with Gradient-Based Sampling
149. ICLR 2025Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
150. ICLR 2025Optimizing Neural Network Representations of Boolean Networks

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.