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 23 / 38 页

  1. NeurIPS 2025Length Generalization via Auxiliary Tasks
  2. NeurIPS 2025Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent
  3. NeurIPS 2025Machine Unlearning under Overparameterization
  4. NeurIPS 2025MAP Estimation with Denoisers: Convergence Rates and Guarantees
  5. NeurIPS 2025Marginal-Nonuniform PAC Learnability
  6. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
  7. NeurIPS 2025Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
  8. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
  9. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
  10. NeurIPS 2025MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
  11. NeurIPS 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
  12. NeurIPS 2025Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
  13. NeurIPS 2025MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
  14. NeurIPS 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
  15. NeurIPS 2025NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
  16. NeurIPS 2025Natural Gradient VI: Guarantees for Non-Conjugate Models
  17. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
  18. NeurIPS 2025Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem
  19. NeurIPS 2025Neural Evolution Strategy for Black-box Pareto Set Learning
  20. NeurIPS 2025New Parallel and Streaming Algorithms for Directed Densest Subgraph
  21. NeurIPS 2025New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results
  22. NeurIPS 2025Non-Clairvoyant Scheduling with Progress Bars
  23. NeurIPS 2025Non-convex entropic mean-field optimization via Best Response flow
  24. NeurIPS 2025Non-Convex Tensor Recovery from Tube-Wise Sensing
  25. NeurIPS 2025Non-monotone Submodular Optimization: $p$-Matchoid Constraints and Fully Dynamic Setting
  26. NeurIPS 2025Non-Singularity of the Gradient Descent Map for Neural Networks with Piecewise Analytic Activations
  27. NeurIPS 2025Non-stationary Bandit Convex Optimization: A Comprehensive Study
  28. NeurIPS 2025Non-Stationary Lipschitz Bandits
  29. NeurIPS 2025Nonlinear Laplacians: Tunable principal component analysis under directional prior information
  30. NeurIPS 2025Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
  31. NeurIPS 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
  32. NeurIPS 2025Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
  33. NeurIPS 2025On Extending Direct Preference Optimization to Accommodate Ties
  34. NeurIPS 2025On Linear Mode Connectivity of Mixture-of-Experts Architectures
  35. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
  36. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
  37. NeurIPS 2025On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent
  38. NeurIPS 2025On the Emergence of Linear Analogies in Word Embeddings
  39. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
  40. NeurIPS 2025On the Robustness of Transformers against Context Hijacking for Linear Classification
  41. NeurIPS 2025On the sample complexity of semi-supervised multi-objective learning
  42. NeurIPS 2025On Traceability in $\ell_p$ Stochastic Convex Optimization
  43. NeurIPS 2025On Transferring Transferability: Towards a Theory for Size Generalization
  44. NeurIPS 2025On Universality Classes of Equivariant Networks
  45. NeurIPS 2025Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
  46. NeurIPS 2025Online Multi-Class Selection with Group Fairness Guarantee
  47. NeurIPS 2025Online Portfolio Selection with ML Predictions
  48. NeurIPS 2025Online Two-Stage Submodular Maximization
  49. NeurIPS 2025Opinion Maximization in Social Networks by Modifying Internal Opinions
  50. NeurIPS 2025OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial 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