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 778 篇，第 11 / 16 页

  1. NeurIPS 2024Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
  2. NeurIPS 2024Directional Smoothness and Gradient Methods: Convergence and Adaptivity
  3. NeurIPS 2024Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
  4. NeurIPS 2024Disentangling Linear Quadratic Control with Untrusted ML Predictions
  5. NeurIPS 2024Distribution Learning with Valid Outputs Beyond the Worst-Case
  6. NeurIPS 2024Distributional Preference Alignment of LLMs via Optimal Transport
  7. NeurIPS 2024DistrictNet: Decision-aware learning for geographical districting
  8. NeurIPS 2024Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
  9. NeurIPS 2024Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
  10. NeurIPS 2024Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
  11. NeurIPS 2024Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
  12. NeurIPS 2024Dual Lagrangian Learning for Conic Optimization
  13. NeurIPS 2024Efficiency of the First-Price Auction in the Autobidding World
  14. NeurIPS 2024Efficient Combinatorial Optimization via Heat Diffusion
  15. NeurIPS 2024Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
  16. NeurIPS 2024Efficient Leverage Score Sampling for Tensor Train Decomposition
  17. NeurIPS 2024Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
  18. NeurIPS 2024Emergence of heavy tails in homogenized stochastic gradient descent
  19. NeurIPS 2024Euclidean distance compression via deep random features
  20. NeurIPS 2024Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
  21. NeurIPS 2024Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
  22. NeurIPS 2024Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
  23. NeurIPS 2024Fair Secretaries with Unfair Predictions
  24. NeurIPS 2024Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
  25. NeurIPS 2024Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
  26. NeurIPS 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
  27. NeurIPS 2024Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
  28. NeurIPS 2024FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
  29. NeurIPS 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
  30. NeurIPS 2024First-Order Methods for Linearly Constrained Bilevel Optimization
  31. NeurIPS 2024First-Order Minimax Bilevel Optimization
  32. NeurIPS 2024Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
  33. NeurIPS 2024From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
  34. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
  35. NeurIPS 2024Functional Bilevel Optimization for Machine Learning
  36. NeurIPS 2024Functionally Constrained Algorithm Solves Convex Simple Bilevel Problem
  37. NeurIPS 2024Fundamental Convergence Analysis of Sharpness-Aware Minimization
  38. NeurIPS 2024Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
  39. NeurIPS 2024Generalized Fast Exact Conformalization
  40. NeurIPS 2024Generic Unsupervised Optimization for a Latent Variable Model With Exponential Family Observables
  41. NeurIPS 2024GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
  42. NeurIPS 2024Gradient Guidance for Diffusion Models: An Optimization Perspective
  43. NeurIPS 2024Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
  44. NeurIPS 2024Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
  45. NeurIPS 2024Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
  46. NeurIPS 2024Hardness of Learning Neural Networks under the Manifold Hypothesis
  47. NeurIPS 2024High-probability complexity bounds for stochastic non-convex minimax optimization
  48. NeurIPS 2024How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
  49. NeurIPS 2024How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
  50. NeurIPS 2024How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective

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