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

1,871 papers, page 31 of 38

1501. NeurIPS 2024Credal Learning Theory
1502. NeurIPS 2024CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
1503. NeurIPS 2024Decision-Focused Learning with Directional Gradients
1504. NeurIPS 2024Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
1505. NeurIPS 2024Deep linear networks for regression are implicitly regularized towards flat minima
1506. NeurIPS 2024Derivatives of Stochastic Gradient Descent in parametric optimization
1507. NeurIPS 2024Diffeomorphic interpolation for efficient persistence-based topological optimization
1508. NeurIPS 2024Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
1509. NeurIPS 2024Directional Smoothness and Gradient Methods: Convergence and Adaptivity
1510. NeurIPS 2024Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
1511. NeurIPS 2024Disentangling Linear Quadratic Control with Untrusted ML Predictions
1512. NeurIPS 2024Distribution Learning with Valid Outputs Beyond the Worst-Case
1513. NeurIPS 2024Distributional Preference Alignment of LLMs via Optimal Transport
1514. NeurIPS 2024DistrictNet: Decision-aware learning for geographical districting
1515. NeurIPS 2024Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
1516. NeurIPS 2024Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
1517. NeurIPS 2024Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
1518. NeurIPS 2024Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
1519. NeurIPS 2024Dual Lagrangian Learning for Conic Optimization
1520. NeurIPS 2024Efficiency of the First-Price Auction in the Autobidding World
1521. NeurIPS 2024Efficient Combinatorial Optimization via Heat Diffusion
1522. NeurIPS 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
1523. NeurIPS 2024Efficient Leverage Score Sampling for Tensor Train Decomposition
1524. NeurIPS 2024Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
1525. NeurIPS 2024Emergence of heavy tails in homogenized stochastic gradient descent
1526. NeurIPS 2024Euclidean distance compression via deep random features
1527. NeurIPS 2024Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
1528. NeurIPS 2024Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
1529. NeurIPS 2024Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
1530. NeurIPS 2024Fair Secretaries with Unfair Predictions
1531. NeurIPS 2024Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
1532. NeurIPS 2024Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
1533. NeurIPS 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
1534. NeurIPS 2024Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
1535. NeurIPS 2024FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
1536. NeurIPS 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
1537. NeurIPS 2024First-Order Methods for Linearly Constrained Bilevel Optimization
1538. NeurIPS 2024First-Order Minimax Bilevel Optimization
1539. NeurIPS 2024Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
1540. NeurIPS 2024From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
1541. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
1542. NeurIPS 2024Functional Bilevel Optimization for Machine Learning
1543. NeurIPS 2024Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
1544. NeurIPS 2024Fundamental Convergence Analysis of Sharpness-Aware Minimization
1545. NeurIPS 2024Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
1546. NeurIPS 2024Generalized Fast Exact Conformalization
1547. NeurIPS 2024Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
1548. NeurIPS 2024GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
1549. NeurIPS 2024Gradient Guidance for Diffusion Models: An Optimization Perspective
1550. NeurIPS 2024Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional 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.