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 6 / 7 页

  1. NeurIPS 2025Robustly Learning Monotone Single-Index Models
  2. NeurIPS 2025SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
  3. NeurIPS 2025Sample-Adaptivity Tradeoff in On-Demand Sampling
  4. NeurIPS 2025Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
  5. NeurIPS 2025Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law
  6. NeurIPS 2025Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
  7. NeurIPS 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
  8. NeurIPS 2025Semi-infinite Nonconvex Constrained Min-Max Optimization
  9. NeurIPS 2025Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization
  10. NeurIPS 2025Sharp Matrix Empirical Bernstein Inequalities
  11. NeurIPS 2025Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings
  12. NeurIPS 2025Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis
  13. NeurIPS 2025Small Singular Values Matter: A Random Matrix Analysis of Transformer Models
  14. NeurIPS 2025Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints
  15. NeurIPS 2025Smoothed Agnostic Learning of Halfspaces over the Hypercube
  16. NeurIPS 2025Solver-Free Decision-Focused Learning for Linear Optimization Problems
  17. NeurIPS 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
  18. NeurIPS 2025Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics
  19. NeurIPS 2025Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation
  20. NeurIPS 2025Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
  21. NeurIPS 2025Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation
  22. NeurIPS 2025Spectral Estimation with Free Decompression
  23. NeurIPS 2025Stab-SGD: Noise-Adaptivity in Smooth Optimization with Stability Ratios
  24. NeurIPS 2025Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
  25. NeurIPS 2025Stochastic Gradients under Nuisances
  26. NeurIPS 2025Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
  27. NeurIPS 2025Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
  28. NeurIPS 2025Streaming Attention Approximation via Discrepancy Theory
  29. NeurIPS 2025Streaming Federated Learning with Markovian Data
  30. NeurIPS 2025Streaming Stochastic Submodular Maximization with On-Demand User Requests
  31. NeurIPS 2025System Prompt Optimization with Meta-Learning
  32. NeurIPS 2025Targeted Maximum Likelihood Learning: An Optimization Perspective
  33. NeurIPS 2025The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective
  34. NeurIPS 2025The Complexity of Finding Local Optima in Contrastive Learning
  35. NeurIPS 2025The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
  36. NeurIPS 2025The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
  37. NeurIPS 2025The Flood Complex: Large-Scale Persistent Homology on Millions of Points
  38. NeurIPS 2025The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
  39. NeurIPS 2025The Persistence of Neural Collapse Despite Low-Rank Bias
  40. NeurIPS 2025The Rich and the Simple: On the Implicit Bias of Adam and SGD
  41. NeurIPS 2025Theoretical Investigation of Adafactor for Non-Convex Smooth Optimization
  42. NeurIPS 2025Tight analyses of first-order methods with error feedback
  43. NeurIPS 2025Tight Asymptotics of Extreme Order Statistics
  44. NeurIPS 2025Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
  45. NeurIPS 2025Tight Lower Bounds and Improved Convergence in Performative Prediction
  46. NeurIPS 2025Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling
  47. NeurIPS 2025Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
  48. NeurIPS 2025Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
  49. NeurIPS 2025Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
  50. NeurIPS 2025TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks

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