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

119 papers, page 2 of 3

51. NeurIPS 2026How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
52. NeurIPS 2026Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
53. NeurIPS 2026Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
54. NeurIPS 2026Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
55. NeurIPS 2026In-Context Black-Box Optimization with Unreliable Feedback
56. NeurIPS 2026In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
57. NeurIPS 2026Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
58. NeurIPS 2026Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
59. NeurIPS 2026KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task
60. NeurIPS 2026Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
61. NeurIPS 2026Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances
62. NeurIPS 2026Learning Polyhedral Conformal Sets for Robust Optimization
63. NeurIPS 2026Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex Functions
64. NeurIPS 2026Learning to Audit ML Models with Theory of Mind
65. NeurIPS 2026Learning to Discover Iterative Spectral Algorithms
66. NeurIPS 2026Linear Contextual Bandits with Quasi-Optimism
67. NeurIPS 2026Linear Ensemble Sampling with Fewer Ensembles
68. NeurIPS 2026Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization
69. NeurIPS 2026Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
70. NeurIPS 2026LOTION: Smoothing the Optimization Landscape for Quantized Training
71. NeurIPS 2026Masked Sobolev Training for Feasibility-Reliable Optimization Proxies
72. NeurIPS 2026Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization
73. NeurIPS 2026Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
74. NeurIPS 2026Minimax Optimization without Spurious Solutions in Optimal Transport Learning
75. NeurIPS 2026MinMax Recurrent Neural Cascades
76. NeurIPS 2026Model Collapse is a Singular Complexity Trajectory
77. NeurIPS 2026Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
78. NeurIPS 2026Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
79. NeurIPS 2026Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
80. NeurIPS 2026On the Convergence of Success Conditioning for Policy Optimization
81. NeurIPS 2026On the Last-Iterate Convergence of Clipped Gradient Methods
82. NeurIPS 2026On the Parallel Optimality of Exponentiated Gradient Descent
83. NeurIPS 2026Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
84. NeurIPS 2026Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
85. NeurIPS 2026PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
86. NeurIPS 2026Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
87. NeurIPS 2026Playing Markov Games Without Observing Payoffs
88. NeurIPS 2026Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
89. NeurIPS 2026Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences
90. NeurIPS 2026Prediction Under Imperfect Compression: A Theory of Approximate MDL
91. NeurIPS 2026Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
92. NeurIPS 2026Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
93. NeurIPS 2026Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
94. NeurIPS 2026Replicable Constrained Bandits
95. NeurIPS 2026Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective
96. NeurIPS 2026Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
97. NeurIPS 2026Robust Statistical Estimators with Bounded Empirical Sensitivity
98. NeurIPS 2026Sample complexity of stochastic optimization with integer variables
99. NeurIPS 2026Second-Order Complexity Theory for Neural Networks
100. NeurIPS 2026Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets

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.