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

每年论文数

各会议论文数

按年份和会议统计

理论 · optimization论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20233746355123
2024304123670494
20253181961479670
20261192442147584

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

全部理论 · optimization论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 778 篇，第 9 / 16 页

  1. NeurIPS 2025Targeted Maximum Likelihood Learning: An Optimization Perspective
  2. NeurIPS 2025The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  3. NeurIPS 2025The Complexity of Finding Local Optima in Contrastive Learning
  4. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
  5. NeurIPS 2025The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
  6. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
  7. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  8. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
  9. NeurIPS 2025The Rich and the Simple: On the Implicit Bias of Adam and SGD
  10. NeurIPS 2025Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization
  11. NeurIPS 2025Tight analyses of first-order methods with error feedback
  12. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
  13. NeurIPS 2025Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
  14. NeurIPS 2025Tight Lower Bounds and Improved Convergence in Performative Prediction
  15. NeurIPS 2025Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
  16. NeurIPS 2025Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
  17. NeurIPS 2025Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
  18. NeurIPS 2025Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
  19. NeurIPS 2025TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
  20. NeurIPS 2025Two Heads are Better than One: Simulating Large Transformers with Small Ones
  21. NeurIPS 2025UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
  22. NeurIPS 2025Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems
  23. NeurIPS 2025Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback
  24. NeurIPS 2025Understanding Data Influence in Reinforcement Finetuning
  25. NeurIPS 2025Understanding outer learning rates in Local SGD
  26. NeurIPS 2025Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem
  27. NeurIPS 2025Uniform Wrappers: Bridging Concave to Quadratizable Functions in Online Optimization
  28. NeurIPS 2025UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems
  29. NeurIPS 2025Unlocking Dataset Distillation with Diffusion Models
  30. NeurIPS 2025Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise
  31. NeurIPS 2025What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization
  32. NeurIPS 2025What Expressivity Theory Misses: Message Passing Complexity for GNNs
  33. NeurIPS 2025What Makes a Reward Model a Good Teacher? An Optimization Perspective
  34. NeurIPS 2025When Does Curriculum Learning Help? A Theoretical Perspective
  35. NeurIPS 2025When majority rules, minority loses: bias amplification of gradient descent
  36. NeurIPS 2025Which Algorithms Have Tight Generalization Bounds?
  37. NeurIPS 2025Zeroth-Order Optimization Finds Flat Minima
  38. NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
  39. NeurIPS 20244+3 Phases of Compute-Optimal Neural Scaling Laws
  40. NeurIPS 2024A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
  41. NeurIPS 2024A Framework for Bilevel Optimization on Riemannian Manifolds
  42. NeurIPS 2024A Globally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
  43. NeurIPS 2024A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
  44. NeurIPS 2024A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
  45. NeurIPS 2024A two-scale Complexity Measure for Deep Learning Models
  46. NeurIPS 2024Accelerating Matroid Optimization through Fast Imprecise Oracles
  47. NeurIPS 2024Accelerating Non-Maximum Suppression: A Graph Theory Perspective
  48. NeurIPS 2024Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
  49. NeurIPS 2024Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
  50. NeurIPS 2024Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「理论与统计」下的其他主题