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 17 / 38 页

  1. ICML 2025An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
  2. ICML 2025Analytical Lyapunov Function Discovery: An RL-based Generative Approach
  3. ICML 2025Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
  4. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
  5. ICML 2025Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
  6. ICML 2025Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
  7. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
  8. ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
  9. ICML 2025Competitively Consistent Clustering
  10. ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
  11. ICML 2025Constrained Online Convex Optimization with Polyak Feasibility Steps
  12. ICML 2025Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
  13. ICML 2025Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
  14. ICML 2025Decoupled SGDA for Games with Intermittent Strategy Communication
  15. ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
  16. ICML 2025Differentiable Quadratic Optimization For the Maximum Independent Set Problem
  17. ICML 2025Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
  18. ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
  19. ICML 2025Discrepancy Minimization in Input-Sparsity Time
  20. ICML 2025Distributed Conformal Prediction via Message Passing
  21. ICML 2025Distributed Event-Based Learning via ADMM
  22. ICML 2025Dueling Convex Optimization with General Preferences
  23. ICML 2025Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization
  24. ICML 2025Efficient Distributed Optimization under Heavy-Tailed Noise
  25. ICML 2025Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
  26. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
  27. ICML 2025End-to-End Learning Framework for Solving Non-Markovian Optimal Control
  28. ICML 2025Enforcing Idempotency in Neural Networks
  29. ICML 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinement
  30. ICML 2025Ensemble Learned Bloom Filters: Two Oracles are Better than One
  31. ICML 2025Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects
  32. ICML 2025Expected Variational Inequalities
  33. ICML 2025Exploiting Curvature in Online Convex Optimization with Delayed Feedback
  34. ICML 2025Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
  35. ICML 2025Extreme Value Policy Optimization for Safe Reinforcement Learning
  36. ICML 2025Fast Tensor Completion via Approximate Richardson Iteration
  37. ICML 2025Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching
  38. ICML 2025Features are fate: a theory of transfer learning in high-dimensional regression
  39. ICML 2025FedECADO: A Dynamical System Model of Federated Learning
  40. ICML 2025Finding Wasserstein Ball Center: Efficient Algorithm and The Applications in Fairness
  41. ICML 2025Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
  42. ICML 2025Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
  43. ICML 2025Fully Dynamic Embedding into $\ell_p$ Spaces
  44. ICML 2025General framework for online-to-nonconvex conversion: Schedule-free SGD is also effective for nonconvex optimization
  45. ICML 2025Generalization of noisy SGD in unbounded non-convex settings
  46. ICML 2025Generalization Performance of Ensemble Clustering: From Theory to Algorithm
  47. ICML 2025Generalized additive models via direct optimization of regularized decision stump forests
  48. ICML 2025Generalized Smooth Bilevel Optimization with Nonconvex Lower-Level
  49. ICML 2025Global curvature for second-order optimization of neural networks
  50. ICML 2025Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs

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