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

584 papers, page 9 of 12

401. ICML 2026Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming
402. ICML 2026Provably Learning Attention with Queries
403. ICML 2026Proximal-Based Generative Modeling for Bayesian Inverse Problems
404. ICML 2026QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypotheses
405. ICML 2026Rational Neural Networks have Expressivity Advantages
406. ICML 2026Reducing Per-Sample Harm in Stochastic Optimization
407. ICML 2026Refined Analysis of Entropy-Regularized Actor-Critic
408. ICML 2026Rethinking Convergence in MoE Training: The Role of Routing Sparsity
409. ICML 2026Rethinking Neural Network Learning Rates: A Stackelberg Perspective
410. ICML 2026Riemannian Dueling Optimization
411. ICML 2026Riemannian Optimization for Fair Spectral Clustering
412. ICML 2026RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
413. ICML 2026Robust AI Evaluation through Maximal Lotteries
414. ICML 2026Robust Learning via Nested Distributionally Robust Optimization
415. ICML 2026Robust Strategic Classification under Decision-Dependent Cost Uncertainty
416. ICML 2026Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
417. ICML 2026Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
418. ICML 2026Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
419. ICML 2026Scaling depth capacity via zero/one-layer model expansion
420. ICML 2026Search Space Synthesis for Parametric Functions
421. ICML 2026Second-Order Bilevel Optimization with Accelerated Convergence Rates
422. ICML 2026Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees
423. ICML 2026Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
424. ICML 2026Sharp Empirical Bernstein Inequalities for the Variance of Bounded Random Variables
425. ICML 2026Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
426. ICML 2026Ski Rental with Distributional Predictions of Unknown Quality
427. ICML 2026Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective
428. ICML 2026Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
429. ICML 2026Solving Imperfect-Recall Games via Sum-of-Squares Optimization
430. ICML 2026Stability Analysis of Sharpness-Aware Minimization
431. ICML 2026Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
432. ICML 2026Statistically Undetectable Backdoors in Deep Neural Networks
433. ICML 2026Steady-State Behavior of Constant-Stepsize Stochastic Approximation: Gaussian Approximation and Tail Bounds
434. ICML 2026Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
435. ICML 2026Stochastic Gradient Methods under Heavy-Tailed Noises in Weakly Convex Optimization
436. ICML 2026Strategy-Aware Optimization Modeling with Reasoning LLMs
437. ICML 2026Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
438. ICML 2026Taming Stochastic Gradient Descent: Almost Sure Convergence and Saddle-Point Avoidance under $(L_{0},L_{1})$-Smoothness
439. ICML 2026Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds
440. ICML 2026The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
441. ICML 2026The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
442. ICML 2026The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
443. ICML 2026The Optimal Sample Complexity of Linear Contracts
444. ICML 2026The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
445. ICML 2026The Theory and Practice of MAP Inference over Non-Convex Constraints
446. ICML 2026The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes
447. ICML 2026Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
448. ICML 2026To Grok Grokking: Provable Grokking in Ridge Regression
449. ICML 2026Towards Atoms of Large Language Models
450. ICML 2026Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis

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.