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 2 of 10

51. ICLR 2024Generative Adversarial Equilibrium Solvers
52. ICLR 2024GIO: Gradient Information Optimization for Training Dataset Selection
53. ICLR 2024Global Optimality for Non-linear Constrained Restoration Problems via Invexity
54. ICLR 2024Grokking as the transition from lazy to rich training dynamics
55. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
56. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
57. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
58. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
59. ICLR 2024Improving Convergence and Generalization Using Parameter Symmetries
60. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
61. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
62. ICLR 2024Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
63. ICLR 2024JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention
64. ICLR 2024Large Language Models to Enhance Bayesian Optimization
65. ICLR 2024Learning to Solve Bilevel Programs with Binary Tender
66. ICLR 2024Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
67. ICLR 2024Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset
68. ICLR 2024Linear attention is (maybe) all you need (to understand Transformer optimization)
69. ICLR 2024Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
70. ICLR 2024Local Composite Saddle Point Optimization
71. ICLR 2024LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models
72. ICLR 2024Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
73. ICLR 2024Magnitude Invariant Parametrizations Improve Hypernetwork Learning
74. ICLR 2024Momentum Benefits Non-iid Federated Learning Simply and Provably
75. ICLR 2024Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss
76. ICLR 2024Near-Optimal Solutions of Constrained Learning Problems
77. ICLR 2024Neur2RO: Neural Two-Stage Robust Optimization
78. ICLR 2024New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
79. ICLR 2024Noisy Interpolation Learning with Shallow Univariate ReLU Networks
80. ICLR 2024On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
81. ICLR 2024On the Effect of Batch Size in Byzantine-Robust Distributed Learning
82. ICLR 2024On the hardness of learning under symmetries
83. ICLR 2024On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
84. ICLR 2024On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
85. ICLR 2024On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
86. ICLR 2024One Forward is Enough for Neural Network Training via Likelihood Ratio Method
87. ICLR 2024OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
88. ICLR 2024Optimal Sample Complexity of Contrastive Learning
89. ICLR 2024Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
90. ICLR 2024Optimistic Bayesian Optimization with Unknown Constraints
91. ICLR 2024Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
92. ICLR 2024PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
93. ICLR 2024Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
94. ICLR 2024Private Zeroth-Order Nonsmooth Nonconvex Optimization
95. ICLR 2024Quadratic models for understanding catapult dynamics of neural networks
96. ICLR 2024Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
97. ICLR 2024Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods
98. ICLR 2024Scaling Convex Neural Networks with Burer-Monteiro Factorization
99. ICLR 2024SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
100. ICLR 2024Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity

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.