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 6 / 16 页

  1. NeurIPS 2025Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning
  2. NeurIPS 2025Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems
  3. NeurIPS 2025High-Dimensional Calibration from Swap Regret
  4. NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
  5. NeurIPS 2025How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
  6. NeurIPS 2025How Memory in Optimization Algorithms Implicitly Modifies the Loss
  7. NeurIPS 2025How Particle System Theory Enhances Hypergraph Message Passing
  8. NeurIPS 2025How to Learn a Star: Binary Classification with Starshaped Polyhedral Sets
  9. NeurIPS 2025How to Scale Second-Order Optimization
  10. NeurIPS 2025Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems
  11. NeurIPS 2025IMPACT: Irregular Multi-Patch Adversarial Composition Based on Two‑Phase Optimization
  12. NeurIPS 2025Improved Algorithms for Fair Matroid Submodular Maximization
  13. NeurIPS 2025Improved Balanced Classification with Theoretically Grounded Loss Functions
  14. NeurIPS 2025Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization
  15. NeurIPS 2025Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning
  16. NeurIPS 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
  17. NeurIPS 2025Isotropic Noise in Stochastic and Quantum Convex Optimization
  18. NeurIPS 2025Kernel von Mises Formula of the Influence Function
  19. NeurIPS 2025Knee-Deep in C-RASP: A Transformer Depth Hierarchy
  20. NeurIPS 2025KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
  21. NeurIPS 2025Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
  22. NeurIPS 2025Last Iterate Convergence in Monotone Mean Field Games
  23. NeurIPS 2025Learning (Approximately) Equivariant Networks via Constrained Optimization
  24. NeurIPS 2025Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems
  25. NeurIPS 2025Learning Expandable and Adaptable Representations for Continual Learning
  26. NeurIPS 2025Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
  27. NeurIPS 2025Learning from Interval Targets
  28. NeurIPS 2025Learning Linear Attention in Polynomial Time
  29. NeurIPS 2025Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling
  30. NeurIPS 2025Learning Provably Improves the Convergence of Gradient Descent
  31. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
  32. NeurIPS 2025Learning to Insert for Constructive Neural Vehicle Routing Solver
  33. NeurIPS 2025Learning with Statistical Equality Constraints
  34. NeurIPS 2025Length Generalization via Auxiliary Tasks
  35. NeurIPS 2025Local Curvature Descent: Squeezing More Curvature out of Standard and Polyak Gradient Descent
  36. NeurIPS 2025Machine Unlearning under Overparameterization
  37. NeurIPS 2025MAP Estimation with Denoisers: Convergence Rates and Guarantees
  38. NeurIPS 2025Marginal-Nonuniform PAC Learnability
  39. NeurIPS 2025Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
  40. NeurIPS 2025Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
  41. NeurIPS 2025Metric Automata Theory: A Unifying Theory of RNNs
  42. NeurIPS 2025MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
  43. NeurIPS 2025MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
  44. NeurIPS 2025Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization
  45. NeurIPS 2025Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning
  46. NeurIPS 2025MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
  47. NeurIPS 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
  48. NeurIPS 2025NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
  49. NeurIPS 2025Natural Gradient VI: Guarantees for Non-Conjugate Models
  50. NeurIPS 2025Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

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