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 27 / 38 页

  1. ICLR 2024Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
  2. ICLR 2024Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
  3. ICLR 2024FOSI: Hybrid First and Second Order Optimization
  4. ICLR 2024General Stability Analysis for Zeroth-Order Optimization Algorithms
  5. ICLR 2024Generative Adversarial Equilibrium Solvers
  6. ICLR 2024GIO: Gradient Information Optimization for Training Dataset Selection
  7. ICLR 2024Global Optimality for Non-linear Constrained Restoration Problems via Invexity
  8. ICLR 2024Grokking as the transition from lazy to rich training dynamics
  9. ICLR 2024How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
  10. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
  11. ICLR 2024Implicit regularization of deep residual networks towards neural ODEs
  12. ICLR 2024Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
  13. ICLR 2024Improving Convergence and Generalization Using Parameter Symmetries
  14. ICLR 2024Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
  15. ICLR 2024Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
  16. ICLR 2024Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
  17. ICLR 2024JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention
  18. ICLR 2024Large Language Models to Enhance Bayesian Optimization
  19. ICLR 2024Learning to Solve Bilevel Programs with Binary Tender
  20. ICLR 2024Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
  21. ICLR 2024Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Lightweight Optimizer and Small-scale Training Dataset
  22. ICLR 2024Linear attention is (maybe) all you need (to understand Transformer optimization)
  23. ICLR 2024Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
  24. ICLR 2024Local Composite Saddle Point Optimization
  25. ICLR 2024LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models
  26. ICLR 2024Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
  27. ICLR 2024Magnitude Invariant Parametrizations Improve Hypernetwork Learning
  28. ICLR 2024Momentum Benefits Non-iid Federated Learning Simply and Provably
  29. ICLR 2024Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss
  30. ICLR 2024Near-Optimal Solutions of Constrained Learning Problems
  31. ICLR 2024Neur2RO: Neural Two-Stage Robust Optimization
  32. ICLR 2024New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
  33. ICLR 2024Noisy Interpolation Learning with Shallow Univariate ReLU Networks
  34. ICLR 2024On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
  35. ICLR 2024On the Effect of Batch Size in Byzantine-Robust Distributed Learning
  36. ICLR 2024On the hardness of learning under symmetries
  37. ICLR 2024On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
  38. ICLR 2024On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
  39. ICLR 2024On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
  40. ICLR 2024One Forward is Enough for Neural Network Training via Likelihood Ratio Method
  41. ICLR 2024OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
  42. ICLR 2024Optimal Sample Complexity of Contrastive Learning
  43. ICLR 2024Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
  44. ICLR 2024Optimistic Bayesian Optimization with Unknown Constraints
  45. ICLR 2024Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
  46. ICLR 2024PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
  47. ICLR 2024Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
  48. ICLR 2024Private Zeroth-Order Nonsmooth Nonconvex Optimization
  49. ICLR 2024Quadratic models for understanding catapult dynamics of neural networks
  50. ICLR 2024Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian 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