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 1,871 篇，第 8 / 38 页

  1. ICML 2026Learning Credal Ensembles via Distributionally Robust Optimization
  2. ICML 2026Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
  3. ICML 2026Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent
  4. ICML 2026Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
  5. ICML 2026Learning the Best Under Constraints: A Duality-Based Framework
  6. ICML 2026Learning-Augmented Online Covering Problems
  7. ICML 2026Learning-Augmented Online Minimization with Dual Predictions
  8. ICML 2026Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
  9. ICML 2026Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
  10. ICML 2026Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noises
  11. ICML 2026LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent
  12. ICML 2026Local Minima in Quadratic-Penalty Relaxations of Binary Linear Programs
  13. ICML 2026Logarithmic Switching Regret for Online Convex Optimization
  14. ICML 2026Low-dimensional topology of deep neural networks
  15. ICML 2026Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
  16. ICML 2026LOZO+: Provably Efficient Zeroth-Order Fine-Tuning via Greedy Low-Rank Subspace Selection
  17. ICML 2026M+Adam: Low-Precision Training via Additive–Multiplicative Optimization
  18. ICML 2026Matroid Algorithms Under Size-Sensitive Independence Oracles
  19. ICML 2026Maximin Relative Improvement: Fair Learning as a Bargaining Problem
  20. ICML 2026Mirror Descent Under Generalized Smoothness
  21. ICML 2026Mirror Mean-Field Langevin Dynamics
  22. ICML 2026Mixtures Closest To A Given Measure: A Semidefinite Programming Approach
  23. ICML 2026Mixtures of geodesic factor analyzers on Riemannian homogeneous spaces
  24. ICML 2026Momentum Further Constrains Sharpness at the Edge of Stochastic Stability
  25. ICML 2026Multicalibration Yields Better Matchings
  26. ICML 2026Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation
  27. ICML 2026Near-Optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representation
  28. ICML 2026Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
  29. ICML 2026Non-Euclidean Gradient Descent Operates at the Edge of Stability
  30. ICML 2026Offline Two-Player Zero-Sum Markov Games with KL Regularization
  31. ICML 2026On Expressive Power of Floating-Point Transformers
  32. ICML 2026On Regret Bounds of Thompson Sampling for Bayesian Optimization
  33. ICML 2026On the Computational Complexity of Performative Prediction
  34. ICML 2026On the Convergence Rate of LoRA Gradient Descent
  35. ICML 2026On the Optimization Trajectory of DeepWalk Embeddings
  36. ICML 2026On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
  37. ICML 2026On the Role of Batch Size in Stochastic Conditional Gradient Methods
  38. ICML 2026On the Variability of Concept Activation Vectors
  39. ICML 2026Operator Splitting with Hamilton-Jacobi-based Proximals
  40. ICML 2026OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling
  41. ICML 2026Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
  42. ICML 2026Optimal Regret for Policy Optimization in Contextual Bandits
  43. ICML 2026Optimal Transport with Symmetry Groups
  44. ICML 2026Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov–Arnold Networks
  45. ICML 2026Optimized Deferral for Imbalanced Settings
  46. ICML 2026OptMaster: A DAG-Based Framework for Formulation and Heuristic Discovery in Optimization
  47. ICML 2026OVLR: Efficient, Scalable, and Robust Training via Output-Level Variance-Reduced Likelihood Ratio
  48. ICML 2026Parameter-Masked Decoupled Optimization for Cross-Domain Class-Incremental Learning
  49. ICML 2026Performative Learning Theory
  50. ICML 2026Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

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