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 7 / 16 页

  1. NeurIPS 2025Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem
  2. NeurIPS 2025Neural Evolution Strategy for Black-box Pareto Set Learning
  3. NeurIPS 2025New Parallel and Streaming Algorithms for Directed Densest Subgraph
  4. NeurIPS 2025New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
  5. NeurIPS 2025Non-Clairvoyant Scheduling with Progress Bars
  6. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
  7. NeurIPS 2025Non-Convex Tensor Recovery from Tube-Wise Sensing
  8. NeurIPS 2025Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
  9. NeurIPS 2025Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
  10. NeurIPS 2025Non-stationary Bandit Convex Optimization: A Comprehensive Study
  11. NeurIPS 2025Non-Stationary Lipschitz Bandits
  12. NeurIPS 2025Nonlinear Laplacians: Tunable principal component analysis under directional prior information
  13. NeurIPS 2025Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
  14. NeurIPS 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
  15. NeurIPS 2025Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
  16. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
  17. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
  18. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
  19. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
  20. NeurIPS 2025On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
  21. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
  22. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
  23. NeurIPS 2025On the Robustness of Transformers against Context Hijacking for Linear Classification
  24. NeurIPS 2025On the sample complexity of semi-supervised multi-objective learning
  25. NeurIPS 2025On Traceability in $\ell_p$ Stochastic Convex Optimization
  26. NeurIPS 2025On Transferring Transferability: Towards a Theory for Size Generalization
  27. NeurIPS 2025On Universality Classes of Equivariant Networks
  28. NeurIPS 2025Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
  29. NeurIPS 2025Online Multi-Class Selection with Group Fairness Guarantee
  30. NeurIPS 2025Online Portfolio Selection with ML Predictions
  31. NeurIPS 2025Online Two-Stage Submodular Maximization
  32. NeurIPS 2025Opinion Maximization in Social Networks by Modifying Internal Opinions
  33. NeurIPS 2025OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization
  34. NeurIPS 2025Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
  35. NeurIPS 2025Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
  36. NeurIPS 2025Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality
  37. NeurIPS 2025Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
  38. NeurIPS 2025Oracle-Efficient Combinatorial Semi-Bandits
  39. NeurIPS 2025Parameter-free Algorithms for the Stochastically Extended Adversarial Model
  40. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
  41. NeurIPS 2025Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
  42. NeurIPS 2025PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
  43. NeurIPS 2025PDPO: Parametric Density Path Optimization
  44. NeurIPS 2025Perturbation Bounds for Low-Rank Inverse Approximations under Noise
  45. NeurIPS 2025PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts
  46. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
  47. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
  48. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
  49. NeurIPS 2025Probing Neural Combinatorial Optimization Models
  50. NeurIPS 2025Problem-Parameter-Free Decentralized Bilevel Optimization

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