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 318 篇，第 2 / 7 页

  1. NeurIPS 2025Can Diffusion Models Disentangle? A Theoretical Perspective
  2. NeurIPS 2025CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization
  3. NeurIPS 2025Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
  4. NeurIPS 2025Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
  5. NeurIPS 2025Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
  6. NeurIPS 2025Constrained Linear Thompson Sampling
  7. NeurIPS 2025Constrained Optimization From a Control Perspective via Feedback Linearization
  8. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
  9. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
  10. NeurIPS 2025Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
  11. NeurIPS 2025Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
  12. NeurIPS 2025Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
  13. NeurIPS 2025Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data
  14. NeurIPS 2025Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares
  15. NeurIPS 2025Convergence Rates of Constrained Expected Improvement
  16. NeurIPS 2025Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers
  17. NeurIPS 2025Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems
  18. NeurIPS 2025Cyclic Counterfactuals under Shift–Scale Interventions
  19. NeurIPS 2025Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
  20. NeurIPS 2025Deep learning for continuous-time stochastic control with jumps
  21. NeurIPS 2025Deep Legendre Transform
  22. NeurIPS 2025Deployment Efficient Reward-Free Exploration with Linear Function Approximation
  23. NeurIPS 2025DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization
  24. NeurIPS 2025Differentiable extensions with rounding guarantees for combinatorial optimization over permutations
  25. NeurIPS 2025Differentiation Through Black-Box Quadratic Programming Solvers
  26. NeurIPS 2025Dimension-adapted Momentum Outscales SGD
  27. NeurIPS 2025Disentangling Hyperedges through the Lens of Category Theory
  28. NeurIPS 2025Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
  29. NeurIPS 2025Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks
  30. NeurIPS 2025Distributionally Robust Feature Selection
  31. NeurIPS 2025Distributionally Robust Performative Optimization
  32. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
  33. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
  34. NeurIPS 2025Effective Neural Approximations for Geometric Optimization Problems
  35. NeurIPS 2025Efficient Adaptive Federated Optimization
  36. NeurIPS 2025Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
  37. NeurIPS 2025Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
  38. NeurIPS 2025Efficient Quadratic Corrections for Frank-Wolfe Algorithms
  39. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
  40. NeurIPS 2025Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
  41. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
  42. NeurIPS 2025Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
  43. NeurIPS 2025Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
  44. NeurIPS 2025Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation
  45. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
  46. NeurIPS 2025Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
  47. NeurIPS 2025Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
  48. NeurIPS 2025Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
  49. NeurIPS 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
  50. NeurIPS 2025Exploring Landscapes for Better Minima along Valleys

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