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 16 / 38 页

  1. ICLR 2025Scalable Decentralized Learning with Teleportation
  2. ICLR 2025Scaling FP8 training to trillion-token LLMs
  3. ICLR 2025Second-Order Min-Max Optimization with Lazy Hessians
  4. ICLR 2025Self-Play Preference Optimization for Language Model Alignment
  5. ICLR 2025SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
  6. ICLR 2025Separation Power of Equivariant Neural Networks
  7. ICLR 2025Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
  8. ICLR 2025SGD with memory: fundamental properties and stochastic acceleration
  9. ICLR 2025Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
  10. ICLR 2025Sharpness-Aware Black-Box Optimization
  11. ICLR 2025Sharpness-Aware Minimization: General Analysis and Improved Rates
  12. ICLR 2025SOAP: Improving and Stabilizing Shampoo using Adam for Language Modeling
  13. ICLR 2025Solving hidden monotone variational inequalities with surrogate losses
  14. ICLR 2025SOREL: A Stochastic Algorithm for Spectral Risks Minimization
  15. ICLR 2025Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance
  16. ICLR 2025Strategic Classification With Externalities
  17. ICLR 2025Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression
  18. ICLR 2025Taming Transformer Without Using Learning Rate Warmup
  19. ICLR 2025The Complexity of Two-Team Polymatrix Games with Independent Adversaries
  20. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
  21. ICLR 2025The Directionality of Optimization Trajectories in Neural Networks
  22. ICLR 2025The Optimization Landscape of SGD Across the Feature Learning Strength
  23. ICLR 2025The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning
  24. ICLR 2025Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
  25. ICLR 2025Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics
  26. ICLR 2025To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
  27. ICLR 2025Towards Faster Decentralized Stochastic Optimization with Communication Compression
  28. ICLR 2025Towards Foundation Models for Mixed Integer Linear Programming
  29. ICLR 2025Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
  30. ICLR 2025Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis
  31. ICLR 2025Understanding Optimization in Deep Learning with Central Flows
  32. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
  33. ICLR 2025Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
  34. ICLR 2025Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
  35. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
  36. ICLR 2025Vertical Federated Learning with Missing Features During Training and Inference
  37. ICLR 2025What should a neuron aim for? Designing local objective functions based on information theory
  38. ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
  39. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  40. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
  41. ICML 2025A Bregman Proximal Viewpoint on Neural Operators
  42. ICML 2025A Generalization Result for Convergence in Learning-to-Optimize
  43. ICML 2025A Near Linear Query Lower Bound for Submodular Maximization
  44. ICML 2025A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
  45. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
  46. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
  47. ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
  48. ICML 2025Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
  49. ICML 2025Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
  50. ICML 2025Aligned Multi Objective 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