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

670 papers, page 12 of 14

551. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
552. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
553. NeurIPS 2025On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
554. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
555. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
556. NeurIPS 2025On the Robustness of Transformers against Context Hijacking for Linear Classification
557. NeurIPS 2025On the sample complexity of semi-supervised multi-objective learning
558. NeurIPS 2025On Traceability in $\ell_p$ Stochastic Convex Optimization
559. NeurIPS 2025On Transferring Transferability: Towards a Theory for Size Generalization
560. NeurIPS 2025On Universality Classes of Equivariant Networks
561. NeurIPS 2025Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
562. NeurIPS 2025Online Multi-Class Selection with Group Fairness Guarantee
563. NeurIPS 2025Online Portfolio Selection with ML Predictions
564. NeurIPS 2025Online Two-Stage Submodular Maximization
565. NeurIPS 2025Opinion Maximization in Social Networks by Modifying Internal Opinions
566. NeurIPS 2025OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization
567. NeurIPS 2025Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
568. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
569. NeurIPS 2025Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
570. NeurIPS 2025Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
571. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
572. NeurIPS 2025Parameter-free Algorithms for the Stochastically Extended Adversarial Model
573. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
574. NeurIPS 2025Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
575. NeurIPS 2025PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
576. NeurIPS 2025PDPO: Parametric Density Path Optimization
577. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
578. NeurIPS 2025PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
579. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
580. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
581. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
582. NeurIPS 2025Probing Neural Combinatorial Optimization Models
583. NeurIPS 2025Problem-Parameter-Free Decentralized Bilevel Optimization
584. NeurIPS 2025Product Distribution Learning with Imperfect Advice
585. NeurIPS 2025Provable Meta-Learning with Low-Rank Adaptations
586. NeurIPS 2025Purest Quantum State Identification
587. NeurIPS 2025Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
588. NeurIPS 2025Quantum Speedups for Minimax Optimization and Beyond
589. NeurIPS 2025Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights
590. NeurIPS 2025Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward
591. NeurIPS 2025Replicable Distribution Testing
592. NeurIPS 2025Replicable Online Learning
593. NeurIPS 2025Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality
594. NeurIPS 2025Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
595. NeurIPS 2025Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
596. NeurIPS 2025Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency
597. NeurIPS 2025Revisiting Agnostic Boosting
598. NeurIPS 2025Revisiting Consensus Error: A Fine-grained Analysis of Local SGD under Second-order Data Heterogeneity
599. NeurIPS 2025Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
600. NeurIPS 2025Revisiting Frank-Wolfe for Structured Nonconvex 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.