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

494 papers, page 3 of 10

101. ICLR 2024Small-scale proxies for large-scale Transformer training instabilities
102. ICLR 2024Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
103. ICLR 2024Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
104. ICLR 2024Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
105. ICLR 2024Stochastic Controlled Averaging for Federated Learning with Communication Compression
106. ICLR 2024SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
107. ICLR 2024Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
108. ICLR 2024Symmetric Single Index Learning
109. ICLR 2024Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration
110. ICLR 2024Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
111. ICLR 2024The Marginal Value of Momentum for Small Learning Rate SGD
112. ICLR 2024Time Fairness in Online Knapsack Problems
113. ICLR 2024Towards Establishing Guaranteed Error for Learned Database Operations
114. ICLR 2024Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
115. ICLR 2024Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
116. ICLR 2024Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
117. ICLR 2024TRAM: Bridging Trust Regions and Sharpness Aware Minimization
118. ICLR 2024Two-timescale Extragradient for Finding Local Minimax Points
119. ICLR 2024Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization
120. ICLR 2024Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
121. ICLR 2024Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration
122. ICLR 2024Why is SAM Robust to Label Noise?
123. ICLR 2024Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
124. ICML 2024A New Theoretical Perspective on Data Heterogeneity in Federated Optimization
125. ICML 2024A sampling theory perspective on activations for implicit neural representations
126. ICML 2024A Statistical Theory of Regularization-Based Continual Learning
127. ICML 2024A Theory of Fault-Tolerant Learning
128. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
129. ICML 2024ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints
130. ICML 2024Advancing Dynamic Sparse Training by Exploring Optimization Opportunities
131. ICML 2024Autonomous Sparse Mean-CVaR Portfolio Optimization
132. ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
133. ICML 2024Bayesian Optimization of Function Networks with Partial Evaluations
134. ICML 2024Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
135. ICML 2024Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers
136. ICML 2024Delving into the Convergence of Generalized Smooth Minimax Optimization
137. ICML 2024Differentiability and Optimization of Multiparameter Persistent Homology
138. ICML 2024DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation
139. ICML 2024Does Label Smoothing Help Deep Partial Label Learning?
140. ICML 2024Double Momentum Method for Lower-Level Constrained Bilevel Optimization
141. ICML 2024Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
142. ICML 2024Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization
143. ICML 2024Federated Optimization with Doubly Regularized Drift Correction
144. ICML 2024Fundamental Benefit of Alternating Updates in Minimax Optimization
145. ICML 2024Generalized Preference Optimization: A Unified Approach to Offline Alignment
146. ICML 2024High-Probability Bound for Non-Smooth Non-Convex Stochastic Optimization with Heavy Tails
147. ICML 2024How Free is Parameter-Free Stochastic Optimization?
148. ICML 2024How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
149. ICML 2024Implicit Bias of AdamW: $\ell_\infty$-Norm Constrained Optimization
150. ICML 2024Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

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.