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

123 papers, page 1 of 3

1. ICLR 2024A Discretization Framework for Robust Contextual Stochastic Optimization
2. ICLR 2024A Fast and Provable Algorithm for Sparse Phase Retrieval
3. ICLR 2024A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging
4. ICLR 2024A Multi-Level Framework for Accelerating Training Transformer Models
5. ICLR 2024A Precise Characterization of SGD Stability Using Loss Surface Geometry
6. ICLR 2024A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
7. ICLR 2024A Quadratic Synchronization Rule for Distributed Deep Learning
8. ICLR 2024A Restoration Network as an Implicit Prior
9. ICLR 2024A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
10. ICLR 2024A Sublinear Adversarial Training Algorithm
11. ICLR 2024Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
12. ICLR 2024Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks
13. ICLR 2024Accelerating Sinkhorn algorithm with sparse Newton iterations
14. ICLR 2024Adaptive Federated Learning with Auto-Tuned Clients
15. ICLR 2024Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning
16. ICLR 2024Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
17. ICLR 2024An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
18. ICLR 2024An improved analysis of per-sample and per-update clipping in federated learning
19. ICLR 2024Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
20. ICLR 2024Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
21. ICLR 2024Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
22. ICLR 2024CO2: Efficient Distributed Training with Full Communication-Computation Overlap
23. ICLR 2024Combining Axes Preconditioners through Kronecker Approximation for Deep Learning
24. ICLR 2024Communication-Efficient Federated Non-Linear Bandit Optimization
25. ICLR 2024Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
26. ICLR 2024Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free Algorithm
27. ICLR 2024Contextual Bandits with Online Neural Regression
28. ICLR 2024Convergence of Bayesian Bilevel Optimization
29. ICLR 2024Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
30. ICLR 2024Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
31. ICLR 2024Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
32. ICLR 2024Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
33. ICLR 2024DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
34. ICLR 2024Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
35. ICLR 2024Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
36. ICLR 2024Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
37. ICLR 2024Distributionally Robust Optimization with Bias and Variance Reduction
38. ICLR 2024Doubly Robust Instance-Reweighted Adversarial Training
39. ICLR 2024Dropout Enhanced Bilevel Training
40. ICLR 2024EControl: Fast Distributed Optimization with Compression and Error Control
41. ICLR 2024Efficient Continual Finite-Sum Minimization
42. ICLR 2024Efficiently Computing Similarities to Private Datasets
43. ICLR 2024Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
44. ICLR 2024Fantastic Generalization Measures are Nowhere to be Found
45. ICLR 2024Fast Equilibrium of SGD in Generic Situations
46. ICLR 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
47. ICLR 2024Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
48. ICLR 2024Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
49. ICLR 2024FOSI: Hybrid First and Second Order Optimization
50. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms

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.