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 196 篇，第 4 / 4 页
- ICLR 2025qNBO: quasi-Newton Meets Bilevel Optimization
- ICLR 2025Quality over Quantity in Attention Layers: When Adding More Heads Hurts
- ICLR 2025Quantum (Inspired) $D^2$-sampling with Applications
- ICLR 2025Rethinking Light Decoder-based Solvers for Vehicle Routing Problems
- ICLR 2025Revisiting Large-Scale Non-convex Distributionally Robust Optimization
- ICLR 2025Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations
- ICLR 2025Robustness of Quantum Algorithms for Nonconvex Optimization
- ICLR 2025Scalable Decentralized Learning with Teleportation
- ICLR 2025Scaling FP8 training to trillion-token LLMs
- ICLR 2025Second-Order Min-Max Optimization with Lazy Hessians
- ICLR 2025Self-Play Preference Optimization for Language Model Alignment
- ICLR 2025SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
- ICLR 2025Separation Power of Equivariant Neural Networks
- ICLR 2025Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
- ICLR 2025SGD with memory: fundamental properties and stochastic acceleration
- ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
- ICLR 2025Sharpness-Aware Black-Box Optimization
- ICLR 2025Sharpness-Aware Minimization: General Analysis and Improved Rates
- ICLR 2025SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling
- ICLR 2025Solving hidden monotone variational inequalities with surrogate losses
- ICLR 2025SOREL: A Stochastic Algorithm for Spectral Risks Minimization
- ICLR 2025Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
- ICLR 2025Strategic Classification With Externalities
- ICLR 2025Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression
- ICLR 2025Taming Transformer Without Using Learning Rate Warmup
- ICLR 2025The Complexity of Two-Team Polymatrix Games with Independent Adversaries
- ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
- ICLR 2025The Directionality of Optimization Trajectories in Neural Networks
- ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
- ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
- ICLR 2025Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
- ICLR 2025Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics
- ICLR 2025To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
- ICLR 2025Towards Faster Decentralized Stochastic Optimization with Communication Compression
- ICLR 2025Towards Foundation Models for Mixed Integer Linear Programming
- ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
- ICLR 2025Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
- ICLR 2025Understanding Optimization in Deep Learning with Central Flows
- ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
- ICLR 2025Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
- ICLR 2025Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
- ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
- ICLR 2025Vertical Federated Learning with Missing Features During Training and Inference
- ICLR 2025What should a neuron aim for? Designing local objective functions based on information theory
- ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
- ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
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。