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

244 papers, page 2 of 5

51. ICLR 2026Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence
52. ICLR 2026Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms
53. ICLR 2026Deep FlexQP: Accelerated Nonlinear Programming via Deep Unfolding
54. ICLR 2026Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks
55. ICLR 2026Deft Scheduling of Dynamic Cloud Workflows with Varying Deadlines via Mixture-of-Experts
56. ICLR 2026DeMo: Decoupled Momentum Optimization
57. ICLR 2026Derandomized Online-to-Non-convex Conversion for Stochastic Weakly Convex Optimization
58. ICLR 2026DES-LOC: Desynced Low Communication Adaptive Optimizers for Foundation Models
59. ICLR 2026DIFFSPARSE: ACCELERATING DIFFUSION TRANSFORMERS WITH LEARNED TOKEN SPARSITY
60. ICLR 2026Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization
61. ICLR 2026Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces
62. ICLR 2026Discounted Online Convex Optimization: Uniform Regret Across a Continuous Interval
63. ICLR 2026Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
64. ICLR 2026Distributionally Robust Linear Regression with Block Lewis Weights
65. ICLR 2026Distributionally Robust Optimization via Generative Ambiguity Modeling
66. ICLR 2026Diversified Multinomial Logit Contextual Bandits
67. ICLR 2026DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
68. ICLR 2026DR-Submodular Maximization with Stochastic Biased Gradients: Classical and Quantum Gradient Algorithms
69. ICLR 2026Dual Optimistic Ascent (PI Control) is the Augmented Lagrangian Method in Disguise
70. ICLR 2026Dynamic Kernel Graph Sparsifiers
71. ICLR 2026Efficient algorithms for Incremental Metric Bipartite Matching
72. ICLR 2026Efficient Resource-Constrained Training of Transformers via Subspace Optimization
73. ICLR 2026Efficient Spatially-Variant Convolution via Differentiable Sparse Kernel Complex
74. ICLR 2026Efficient Submodular Maximization for Sums of Concave over Modular Functions
75. ICLR 2026Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
76. ICLR 2026Enhancing Communication Compression via Discrepancy-aware Calibration for Federated Learning
77. ICLR 2026Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation
78. ICLR 2026Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
79. ICLR 2026Error Feedback for Muon and Friends
80. ICLR 2026Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
81. ICLR 2026Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
82. ICLR 2026Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
83. ICLR 2026Fantastic Pretraining Optimizers and Where to Find Them
84. ICLR 2026Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws
85. ICLR 2026Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
86. ICLR 2026Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization
87. ICLR 2026FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
88. ICLR 2026FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models
89. ICLR 2026FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming
90. ICLR 2026FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theory
91. ICLR 2026From Fields to Random Trees
92. ICLR 2026From Sequential to Parallel: Reformulating Dynamic Programming as GPU Kernels for Large-Scale Stochastic Combinatorial Optimization
93. ICLR 2026Gaussian certified unlearning in high dimensions: A hypothesis testing approach
94. ICLR 2026Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
95. ICLR 2026Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Optimization
96. ICLR 2026Globally aware optimization with resurgence
97. ICLR 2026GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs
98. ICLR 2026Gradient Descent with Large Step Sizes: Chaos and Fractal Convergence Region
99. ICLR 2026Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective
100. ICLR 2026Gradient-Normalized Smoothness for Optimization with Approximate Hessians

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.