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 20 of 38

951. NeurIPS 2025A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
952. NeurIPS 2025A Theory for Worst-Case vs. Average-Case Guarantees for LLMs
953. NeurIPS 2025A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond
954. NeurIPS 2025A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
955. NeurIPS 2025Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
956. NeurIPS 2025Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
957. NeurIPS 2025Accelerating Model-Free Optimization via Averaging of Cost Samples
958. NeurIPS 2025Accelerating Optimization via Differentiable Stopping Time
959. NeurIPS 2025Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space
960. NeurIPS 2025Adam Reduces a Unique Form of Sharpness: Theoretical Insights Near the Minimizer Manifold
961. NeurIPS 2025Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
962. NeurIPS 2025Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
963. NeurIPS 2025Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing
964. NeurIPS 2025Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance
965. NeurIPS 2025Agnostic Active Learning Is Always Better Than Passive Learning
966. NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
967. NeurIPS 2025An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds
968. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
969. NeurIPS 2025An Ellipsoid Algorithm for Online Convex Optimization
970. NeurIPS 2025Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
971. NeurIPS 2025Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses
972. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
973. NeurIPS 2025ASGO: Adaptive Structured Gradient Optimization
974. NeurIPS 2025Attention-based clustering
975. NeurIPS 2025Autoencoding Random Forests
976. NeurIPS 2025Balancing Gradient and Hessian Queries in Non-Convex Optimization
977. NeurIPS 2025Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble
978. NeurIPS 2025Benign Overfitting in Single-Head Attention
979. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
980. NeurIPS 2025Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
981. NeurIPS 2025Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
982. NeurIPS 2025Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
983. NeurIPS 2025Block Coordinate Descent for Neural Networks Provably Finds Global Minima
984. NeurIPS 2025Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport
985. NeurIPS 2025Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks
986. NeurIPS 2025CAMO: Convergence-Aware Multi-Fidelity Bayesian Optimization
987. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
988. NeurIPS 2025CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization
989. NeurIPS 2025Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
990. NeurIPS 2025Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
991. NeurIPS 2025Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
992. NeurIPS 2025Constrained Linear Thompson Sampling
993. NeurIPS 2025Constrained Optimization From a Control Perspective via Feedback Linearization
994. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
995. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
996. NeurIPS 2025Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
997. NeurIPS 2025Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
998. NeurIPS 2025Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
999. NeurIPS 2025Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data
1000. NeurIPS 2025Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares

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.