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 11 / 38 页

  1. NeurIPS 2026Fixed Universal Transformers
  2. NeurIPS 2026Follow the Regularized Leader Does Not Converge in Constrained Optimization
  3. NeurIPS 2026Foundations of Categorical Equivariant Deep Learning
  4. NeurIPS 2026From Cursed to Competitive: Closing the ZO–FO Gap via Input-to-State Stability
  5. NeurIPS 2026From SGD to Muon: Adaptive Optimization via Schatten-p Norms
  6. NeurIPS 2026Functional Gradient Descent with Adaptive Representations
  7. NeurIPS 2026Generalization Without Compression Penalty: A Stability Analysis of Error Feedback
  8. NeurIPS 2026Generating in the Limit with Infinitely Many Hallucinations
  9. NeurIPS 2026Global Convergence in Deep Networks via the Second Law of Thermodynamics
  10. NeurIPS 2026Gradient Regularized Newton Boosting Trees with Global Convergence
  11. NeurIPS 2026Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
  12. NeurIPS 2026Group Distributionally Robust Optimization with Flexible Sample Queries
  13. NeurIPS 2026Guaranteed Noisy CP Tensor Recovery via Riemannian Optimization on the Segre Manifold
  14. NeurIPS 2026High dimensional theory of two-phase optimizers
  15. NeurIPS 2026High-arity Sample Compression
  16. NeurIPS 2026How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization
  17. NeurIPS 2026Imperfect Influence, Reliable Rankings: A Theory of TRAK for Data Attribution
  18. NeurIPS 2026Improved Regret Analysis For Parallel Gaussian Process Bandit Optimization
  19. NeurIPS 2026Improving the Optimization Landscape of Matrix Completion with $\epsilon$-close Surrogates
  20. NeurIPS 2026In-Context Black-Box Optimization with Unreliable Feedback
  21. NeurIPS 2026In-Expectation Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise
  22. NeurIPS 2026Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
  23. NeurIPS 2026Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
  24. NeurIPS 2026KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task
  25. NeurIPS 2026Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
  26. NeurIPS 2026Learning Acceptable Lotteries via Queries: Minimizing Aggregated Violation Distances
  27. NeurIPS 2026Learning Polyhedral Conformal Sets for Robust Optimization
  28. NeurIPS 2026Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex Functions
  29. NeurIPS 2026Learning to Audit ML Models with Theory of Mind
  30. NeurIPS 2026Learning to Discover Iterative Spectral Algorithms
  31. NeurIPS 2026Linear Contextual Bandits with Quasi-Optimism
  32. NeurIPS 2026Linear Ensemble Sampling with Fewer Ensembles
  33. NeurIPS 2026Locally-Additive Regret for Delayed Non-stationary Bandit Convex Optimization
  34. NeurIPS 2026Look Before You Leap: Self-Evolving Clinical Reasoning with Psychometric Preference Optimization for Radiology Report Generation
  35. NeurIPS 2026LOTION: Smoothing the Optimization Landscape for Quantized Training
  36. NeurIPS 2026Masked Sobolev Training for Feasibility-Reliable Optimization Proxies
  37. NeurIPS 2026Median-of-Means under Structured Heavy-Tailed Noise: High-Probability Bounds for Clipped Stochastic Optimization
  38. NeurIPS 2026Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
  39. NeurIPS 2026Minimax Optimization without Spurious Solutions in Optimal Transport Learning
  40. NeurIPS 2026MinMax Recurrent Neural Cascades
  41. NeurIPS 2026Model Collapse is a Singular Complexity Trajectory
  42. NeurIPS 2026Nerve-Skeleton Message Passing for Federated Optimization with Overlapping Parameters
  43. NeurIPS 2026Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise
  44. NeurIPS 2026Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
  45. NeurIPS 2026On the Convergence of Success Conditioning for Policy Optimization
  46. NeurIPS 2026On the Last-Iterate Convergence of Clipped Gradient Methods
  47. NeurIPS 2026On the Parallel Optimality of Exponentiated Gradient Descent
  48. NeurIPS 2026Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
  49. NeurIPS 2026Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
  50. NeurIPS 2026PACE: Partial-state Amortized Constraint Editing for Neural 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