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 584 篇，第 10 / 12 页

  1. ICML 2026Towards Parameter-Free Temporal Difference Learning
  2. ICML 2026Towards Understanding Adam Convergence on Highly Degenerate Polynomials
  3. ICML 2026Towards Understanding Generalization of Federated Adversarial Learning: Perspective of Algorithmic Stability
  4. ICML 2026Trainable Nonexpansive Denoisers for Contractive Image Reconstruction
  5. ICML 2026Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
  6. ICML 2026TSP with Predictions: Heatmap to Tour with Provable Guarantees
  7. ICML 2026Understanding MARS: When Scaling Momentum Provably Helps
  8. ICML 2026Understanding SAM through Minimax Perspective
  9. ICML 2026Universal Learning of Nonlinear Dynamics
  10. ICML 2026Universal Representation of Generalized Convex Functions and their Gradients
  11. ICML 2026Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
  12. ICML 2026Variance-Reduced $(\varepsilon, \delta)-$Unlearning using Forget Set Gradients
  13. ICML 2026What Does Preference Learning Recover from Pairwise Comparison Data?
  14. ICML 2026What Does Thompson Sampling Optimize?
  15. ICML 2026Why Do We Need Warm-up? A Theoretical Perspective
  16. NeurIPS 2026A Computational Perspective to Data Ablation Experiments
  17. NeurIPS 2026A Doubly Smoothed Decentralized Stochastic Minimax Optimization Algorithm
  18. NeurIPS 2026A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning
  19. NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
  20. NeurIPS 2026A Near-optimal SQ Lower Bound for Smoothed Agnostic Learning of Boolean Halfspaces
  21. NeurIPS 2026A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts
  22. NeurIPS 2026A Theory of Adversary-Directed Online Learning
  23. NeurIPS 2026A Theory of Spatial Continuous Attractors in Hopfield Energy Landscapes
  24. NeurIPS 2026A Theory of Training Profit-Optimal LLMs
  25. NeurIPS 2026A Theory on Flow Matching with Neural Networks
  26. NeurIPS 2026A Unified Spectral Theory of Multimodal Losses
  27. NeurIPS 2026Accelerating Neural Network Training with Augmented Koopman Dynamics
  28. NeurIPS 2026Achieving Directional-Stationarity from a Single Random Direction Step
  29. NeurIPS 2026Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
  30. NeurIPS 2026Approximate Envy-Free Allocations up to any k Goods
  31. NeurIPS 2026Avoiding Obfuscation with Prover-Estimator Debate
  32. NeurIPS 2026Best Arm Identification for Bandits with Shifting Means
  33. NeurIPS 2026Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
  34. NeurIPS 2026Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
  35. NeurIPS 2026Canonical Predictive Quotients: A Theory of Prediction under Hidden Predictive State Uncertainty with ICL Implications
  36. NeurIPS 2026Characterizing Learning in Deep Neural Networks using a Tractable Algorithmic Complexity Estimator
  37. NeurIPS 2026Closed-Form Last Layer Optimization
  38. NeurIPS 2026Complex Schrödinger Bridges
  39. NeurIPS 2026Continuous p-adic Optimization
  40. NeurIPS 2026Curvature-Dependent Lower Bounds for Riemannian Online Convex Optimization
  41. NeurIPS 2026Decentralized Coupled Representation Learning
  42. NeurIPS 2026Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
  43. NeurIPS 2026Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
  44. NeurIPS 2026DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance
  45. NeurIPS 2026Disentangling Optimization Geometry via Hierarchical Polar Adapters for Class-Incremental Learning
  46. NeurIPS 2026ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
  47. NeurIPS 2026Estimating Implicit Regularization in Deep Learning
  48. NeurIPS 2026Federated Distributionally Robust Neural Combinatorial Optimization with Convergence Guarantees
  49. NeurIPS 2026Finding Simple Proofs for First-Order Optimization
  50. NeurIPS 2026First-Order Regret for Online Convex Optimization with Memory and Online Nonstochastic Control

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