理论 · optimization论文趋势 2023–2026
学习理论及相关：optimization
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,871 篇被归入该主题的论文。
主要结论
- 理论 · optimization论文从 2023 年的 123 篇增长到 2026 年的 584 篇，三年间扩大到约 4.7 倍。
- NeurIPS 是发理论 · optimization论文最多的会议，2023–2026 年共 778 篇，占四个会议总量的 42%。
- 交叉方向里涨得最快的是低秩适配：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 31 篇。
- 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的理论 · learning theory是 5.6 倍，理论 · optimization是 4.7 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 37 | 46 | 35 | 5 | 123 |
| 2024 | 304 | 123 | 67 | 0 | 494 |
| 2025 | 318 | 196 | 147 | 9 | 670 |
| 2026 | 119 | 244 | 214 | 7 | 584 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- 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++
全部理论 · optimization论文
共 609 篇，第 7 / 13 页
- ICLR 2025Does SGD really happen in tiny subspaces?
- ICLR 2025DON’T STOP ME NOW: EMBEDDING BASED SCHEDULING FOR LLMS
- ICLR 2025DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints
- ICLR 2025DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
- ICLR 2025Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation
- ICLR 2025Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
- ICLR 2025Efficient Sparse PCA via Block-Diagonalization
- ICLR 2025Efficient stagewise pretraining via progressive subnetworks
- ICLR 2025Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
- ICLR 2025Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions
- ICLR 2025Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality
- ICLR 2025Fair Submodular Cover
- ICLR 2025Faster Algorithms for Structured Linear and Kernel Support Vector Machines
- ICLR 2025Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimization
- ICLR 2025Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
- ICLR 2025FLOPS: Forward Learning with OPtimal Sampling
- ICLR 2025From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ
- ICLR 2025From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
- ICLR 2025GeoLoRA: Geometric integration for parameter efficient fine-tuning
- ICLR 2025Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture
- ICLR 2025Gradient correlation is a key ingredient to accelerate SGD with momentum
- ICLR 2025Gradient descent with generalized Newton’s method
- ICLR 2025Graph Assisted Offline-Online Deep Reinforcement Learning for Dynamic Workflow Scheduling
- ICLR 2025Group Distributionally Robust Dataset Distillation with Risk Minimization
- ICLR 2025How Gradient descent balances features: A dynamical analysis for two-layer neural networks
- ICLR 2025How many samples are needed to train a deep neural network?
- ICLR 2025How Much is Unseen Depends Chiefly on Information About the Seen
- ICLR 2025Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression
- ICLR 2025Improved Approximation Algorithms for $k$-Submodular Maximization via Multilinear Extension
- ICLR 2025Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
- ICLR 2025Joint Gradient Balancing for Data Ordering in Finite-Sum Multi-Objective Optimization
- ICLR 2025LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace
- ICLR 2025Lasso Bandit with Compatibility Condition on Optimal Arm
- ICLR 2025Last Iterate Convergence of Incremental Methods as a Model of Forgetting
- ICLR 2025LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
- ICLR 2025Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability
- ICLR 2025Learning Hierarchical Polynomials of Multiple Nonlinear Features
- ICLR 2025Learning High-Degree Parities: The Crucial Role of the Initialization
- ICLR 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
- ICLR 2025Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
- ICLR 2025Learning-Augmented Search Data Structures
- ICLR 2025Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling
- ICLR 2025Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
- ICLR 2025Leveraging Variable Sparsity to Refine Pareto Stationarity in Multi-Objective Optimization
- ICLR 2025Linear Partial Gromov-Wasserstein Embedding
- ICLR 2025LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
- ICLR 2025Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
- ICLR 2025Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
- ICLR 2025Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression
- ICLR 2025LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查理论 · optimization在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "theory-optimization"}
常见问题
- 2023–2026 年四大会议一共有多少篇理论 · optimization论文？
- 共 1,871 篇，按年份分别是 2023 年 123 篇、2024 年 494 篇、2025 年 670 篇、2026 年 584 篇。
- NeurIPS 2026 有多少篇理论 · optimization论文？
- NeurIPS 2026 有 119 篇理论 · optimization论文，上一届是 318 篇。
- ICLR 2026 有多少篇理论 · optimization论文？
- ICLR 2026 有 244 篇理论 · optimization论文，上一届是 196 篇。
- ICML 2026 有多少篇理论 · optimization论文？
- ICML 2026 有 214 篇理论 · optimization论文，上一届是 147 篇。
- CVPR 2026 有多少篇理论 · optimization论文？
- CVPR 2026 有 7 篇理论 · optimization论文，上一届是 9 篇。
- 哪个会议的理论 · optimization论文最多？
- NeurIPS，2023–2026 年共 778 篇。