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 584 篇，第 7 / 12 页

  1. ICML 2026Decision Tree Learning on Product Spaces
  2. ICML 2026Decision-Focused Learning via Tangent-Space Projection of Prediction Error
  3. ICML 2026Deep Networks Learn Deep Hierarchical Models
  4. ICML 2026Distributional Alignment Games for Answer-Level Fine-Tuning
  5. ICML 2026DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and Its Loss' Convexity is Dispensable)
  6. ICML 2026DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective Learning
  7. ICML 2026Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
  8. ICML 2026Effective Model Pruning : Measuring the Redundancy of Model Components
  9. ICML 2026Enhancing LLM Training via Spectral Clipping
  10. ICML 2026Equilibrium Pricing in Oligopolistic Data Markets
  11. ICML 2026Error Propagation in Dynamic Programming: From Stochastic Control to American Option Pricing
  12. ICML 2026Exploiting weight-space symmetries for approximating curvature
  13. ICML 2026Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
  14. ICML 2026Failure-Driven Workflow Refinement
  15. ICML 2026Federated Bilevel Performative Prediction
  16. ICML 2026Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
  17. ICML 2026Flat Minima and Generalization: Insights from Stochastic Convex Optimization
  18. ICML 2026Flatness-Aware Stochastic Gradient Langevin Dynamics
  19. ICML 2026FOAM: Frequency and Operator-Error Based Adaptive Damping Method for Reducing Staleness-Oriented Error for Shampoo
  20. ICML 2026From Muon to Gluon: Bridging Theory and Practice of LMO-based Optimizers for LLMs
  21. ICML 2026Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning
  22. ICML 2026General Analysis of LMO-based Optimizers: Beyond Bounded Variance
  23. ICML 2026Geometric Convergence of Gauss–Newton for Neural Networks: Riemannian Geometry and Adaptive Damping
  24. ICML 2026Geometric Rate–Distortion Invariance for Domain Generalization
  25. ICML 2026Geometry-Misalignment in Distributional Learning
  26. ICML 2026Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
  27. ICML 2026Gradient Flow Sampler-based Distributionally Robust Optimization
  28. ICML 2026Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization
  29. ICML 2026Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
  30. ICML 2026Harmful Overfitting in Sobolev Spaces
  31. ICML 2026Hierarchical Representations for Cross-task Automated Heuristic Design using LLMs
  32. ICML 2026High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
  33. ICML 2026High-Probability Convergence Guarantees of Decentralized SGD
  34. ICML 2026Hom-PGD$^+$: Fast Reparameterized Optimization over Non-convex Ball-Homeomorphic Set
  35. ICML 2026How Can Mamba Learn In Context with Outliers and Generalize Provably?
  36. ICML 2026Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks
  37. ICML 2026Improved Convergence Analysis of Topology Dependence in Decentralized SGD
  38. ICML 2026Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variation
  39. ICML 2026Improved Distribution Estimation in $\ell_\infty$
  40. ICML 2026Improved Stochastic Optimization of LogSumExp
  41. ICML 2026Improving the Robustness-Utility Trade-off in Decentralized Learning over Sparse Networks
  42. ICML 2026In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
  43. ICML 2026Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
  44. ICML 2026Is Spurious Correlation Removal Always Learnable?
  45. ICML 2026Iterative Robust Satisficing: Minimizing Performance Degradation Under Distribution Shift
  46. ICML 2026ITSPACE: Monotone Gaussian Optimal Transport Updates
  47. ICML 2026Joint-Space Empowerment as a Theory of Dexterous Motor Coordination
  48. ICML 2026L-SR1: Learned Symmetric-Rank-One Preconditioning
  49. ICML 2026Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem
  50. ICML 2026Learn to change the world: Multi-level reinforcement learning with model-changing actions

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