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 11 of 14

501. NeurIPS 2025Kernel von Mises Formula of the Influence Function
502. NeurIPS 2025Knee-Deep in C-RASP: A Transformer Depth Hierarchy
503. NeurIPS 2025KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
504. NeurIPS 2025Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
505. NeurIPS 2025Last Iterate Convergence in Monotone Mean Field Games
506. NeurIPS 2025Learning (Approximately) Equivariant Networks via Constrained Optimization
507. NeurIPS 2025Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems
508. NeurIPS 2025Learning Expandable and Adaptable Representations for Continual Learning
509. NeurIPS 2025Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
510. NeurIPS 2025Learning from Interval Targets
511. NeurIPS 2025Learning Linear Attention in Polynomial Time
512. NeurIPS 2025Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
513. NeurIPS 2025Learning Provably Improves the Convergence of Gradient Descent
514. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
515. NeurIPS 2025Learning to Insert for Constructive Neural Vehicle Routing Solver
516. NeurIPS 2025Learning with Statistical Equality Constraints
517. NeurIPS 2025Length Generalization via Auxiliary Tasks
518. NeurIPS 2025Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent
519. NeurIPS 2025Machine Unlearning under Overparameterization
520. NeurIPS 2025MAP Estimation with Denoisers: Convergence Rates and Guarantees
521. NeurIPS 2025Marginal-Nonuniform PAC Learnability
522. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
523. NeurIPS 2025Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
524. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
525. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
526. NeurIPS 2025MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
527. NeurIPS 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
528. NeurIPS 2025Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
529. NeurIPS 2025MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
530. NeurIPS 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
531. NeurIPS 2025NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
532. NeurIPS 2025Natural Gradient VI: Guarantees for Non-Conjugate Models
533. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
534. NeurIPS 2025Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem
535. NeurIPS 2025Neural Evolution Strategy for Black-box Pareto Set Learning
536. NeurIPS 2025New Parallel and Streaming Algorithms for Directed Densest Subgraph
537. NeurIPS 2025New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
538. NeurIPS 2025Non-Clairvoyant Scheduling with Progress Bars
539. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
540. NeurIPS 2025Non-Convex Tensor Recovery from Tube-Wise Sensing
541. NeurIPS 2025Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
542. NeurIPS 2025Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
543. NeurIPS 2025Non-stationary Bandit Convex Optimization: A Comprehensive Study
544. NeurIPS 2025Non-Stationary Lipschitz Bandits
545. NeurIPS 2025Nonlinear Laplacians: Tunable principal component analysis under directional prior information
546. NeurIPS 2025Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
547. NeurIPS 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
548. NeurIPS 2025Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
549. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
550. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures

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.