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 5 / 16 页

  1. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
  2. NeurIPS 2025Dynamic Regret Reduces to Kernelized Static Regret
  3. NeurIPS 2025Effective Neural Approximations for Geometric Optimization Problems
  4. NeurIPS 2025Efficient Adaptive Federated Optimization
  5. NeurIPS 2025Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
  6. NeurIPS 2025Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
  7. NeurIPS 2025Efficient Quadratic Corrections for Frank-Wolfe Algorithms
  8. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
  9. NeurIPS 2025Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
  10. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
  11. NeurIPS 2025Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models
  12. NeurIPS 2025Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
  13. NeurIPS 2025Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation
  14. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
  15. NeurIPS 2025Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
  16. NeurIPS 2025Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
  17. NeurIPS 2025Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses
  18. NeurIPS 2025Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
  19. NeurIPS 2025Exploring Landscapes for Better Minima along Valleys
  20. NeurIPS 2025Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
  21. NeurIPS 2025Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
  22. NeurIPS 2025Fairness-Regularized Online Optimization with Switching Costs
  23. NeurIPS 2025Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime
  24. NeurIPS 2025Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
  25. NeurIPS 2025Fast Zeroth-Order Convex Optimization with Quantum Gradient Methods
  26. NeurIPS 2025Faster Algorithms for Structured John Ellipsoid Computation
  27. NeurIPS 2025Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints
  28. NeurIPS 2025Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW
  29. NeurIPS 2025Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds
  30. NeurIPS 2025Flat Channels to Infinity in Neural Loss Landscapes
  31. NeurIPS 2025Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems
  32. NeurIPS 2025Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
  33. NeurIPS 2025FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing
  34. NeurIPS 2025FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization
  35. NeurIPS 2025FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
  36. NeurIPS 2025Gaussian Approximation and Concentration of Constant Learning-Rate Stochastic Gradient Descent
  37. NeurIPS 2025Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits
  38. NeurIPS 2025Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming
  39. NeurIPS 2025Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
  40. NeurIPS 2025GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
  41. NeurIPS 2025Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks
  42. NeurIPS 2025Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies
  43. NeurIPS 2025Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
  44. NeurIPS 2025Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
  45. NeurIPS 2025Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions
  46. NeurIPS 2025Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
  47. NeurIPS 2025HEIR: Learning Graph-Based Motion Hierarchies
  48. NeurIPS 2025Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
  49. NeurIPS 2025Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
  50. NeurIPS 2025Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints

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