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

463 papers, page 7 of 10

301. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
302. ICML 2025Modular Duality in Deep Learning
303. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
304. ICML 2025Multiobjective distribution matching
305. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
306. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
307. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
308. ICML 2025On Differential Privacy for Adaptively Solving Search Problems via Sketching
309. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
310. ICML 2025On the Local Complexity of Linear Regions in Deep ReLU Networks
311. ICML 2025Online Conformal Prediction via Online Optimization
312. ICML 2025Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
313. ICML 2025Optimization for Neural Operators can Benefit from Width
314. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
315. ICML 2025OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
316. ICML 2025PARQ: Piecewise-Affine Regularized Quantization
317. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
318. ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
319. ICML 2025Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
320. ICML 2025Position: A Theory of Deep Learning Must Include Compositional Sparsity
321. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
322. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
323. ICML 2025Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
324. ICML 2025Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
325. ICML 2025Procurement Auctions via Approximately Optimal Submodular Optimization
326. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
327. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
328. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
329. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
330. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
331. ICML 2025Robust Sparsification via Sensitivity
332. ICML 2025ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
333. ICML 2025Safe-EF: Error Feedback for Non-smooth Constrained Optimization
334. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
335. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
336. ICML 2025Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
337. ICML 2025Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
338. ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
339. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
340. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
341. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
342. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
343. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
344. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
345. ICML 2025SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
346. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
347. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
348. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
349. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
350. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

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.