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 18 of 38

851. ICML 2025Graph-Based Algorithms for Diverse Similarity Search
852. ICML 2025Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization
853. ICML 2025Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
854. ICML 2025High-Dimensional Prediction for Sequential Decision Making
855. ICML 2025Identifying Metric Structures of Deep Latent Variable Models
856. ICML 2025Improved Approximations for Hard Graph Problems using Predictions
857. ICML 2025Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization
858. ICML 2025Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
859. ICML 2025Incorporating Arbitrary Matrix Group Equivariance into KANs
860. ICML 2025Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
861. ICML 2025Inverse Optimization via Learning Feasible Regions
862. ICML 2025Joint Learning of Energy-based Models and their Partition Function
863. ICML 2025Joker: Joint Optimization Framework for Lightweight Kernel Machines
864. ICML 2025Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
865. ICML 2025Learning Configurations for Data-Driven Multi-Objective Optimization
866. ICML 2025Learning Minimum-Size BDDs: Towards Efficient Exact Algorithms
867. ICML 2025Learning Mixtures of Experts with EM: A Mirror Descent Perspective
868. ICML 2025Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems
869. ICML 2025Learning with Exact Invariances in Polynomial Time
870. ICML 2025Learning-Augmented Hierarchical Clustering
871. ICML 2025LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail)
872. ICML 2025Loss Functions and Operators Generated by f-Divergences
873. ICML 2025MARS: Unleashing the Power of Variance Reduction for Training Large Models
874. ICML 2025Matrix Completion with Incomplete Side Information via Orthogonal Complement Projection
875. ICML 2025Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
876. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
877. ICML 2025Modular Duality in Deep Learning
878. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
879. ICML 2025Multiobjective distribution matching
880. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
881. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
882. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
883. ICML 2025On Differential Privacy for Adaptively Solving Search Problems via Sketching
884. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
885. ICML 2025On the Local Complexity of Linear Regions in Deep ReLU Networks
886. ICML 2025Online Conformal Prediction via Online Optimization
887. ICML 2025Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
888. ICML 2025Optimization for Neural Operators can Benefit from Width
889. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
890. ICML 2025OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
891. ICML 2025PARQ: Piecewise-Affine Regularized Quantization
892. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
893. ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
894. ICML 2025Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
895. ICML 2025Position: A Theory of Deep Learning Must Include Compositional Sparsity
896. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
897. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
898. ICML 2025Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
899. ICML 2025Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
900. ICML 2025Procurement Auctions via Approximately Optimal Submodular 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.