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 670 篇，第 5 / 14 页

  1. ICLR 2025Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
  2. ICLR 2025Vertical Federated Learning with Missing Features During Training and Inference
  3. ICLR 2025What should a neuron aim for? Designing local objective functions based on information theory
  4. ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
  5. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
  6. ICML 2025$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
  7. ICML 2025A Bregman Proximal Viewpoint on Neural Operators
  8. ICML 2025A Generalization Result for Convergence in Learning-to-Optimize
  9. ICML 2025A Near Linear Query Lower Bound for Submodular Maximization
  10. ICML 2025A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
  11. ICML 2025A Parametric Contextual Online Learning Theory of Brokerage
  12. ICML 2025A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
  13. ICML 2025Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
  14. ICML 2025Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
  15. ICML 2025Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations
  16. ICML 2025Aligned Multi Objective Optimization
  17. ICML 2025An in depth look at the Procrustes-Wasserstein distance: properties and barycenters
  18. ICML 2025Analytical Lyapunov Function Discovery: An RL-based Generative Approach
  19. ICML 2025Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
  20. ICML 2025Automatic Differentiation of Optimization Algorithms with Time-Varying Updates
  21. ICML 2025Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
  22. ICML 2025Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity
  23. ICML 2025Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts
  24. ICML 2025Compact Matrix Quantum Group Equivariant Neural Networks
  25. ICML 2025Competitively Consistent Clustering
  26. ICML 2025Consensus Is All You Get: The Role of Attention in Transformers
  27. ICML 2025Constrained Online Convex Optimization with Polyak Feasibility Steps
  28. ICML 2025Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization
  29. ICML 2025Convergence of Policy Mirror Descent Beyond Compatible Function Approximation
  30. ICML 2025Decoupled SGDA for Games with Intermittent Strategy Communication
  31. ICML 2025Deep Sturm–Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions
  32. ICML 2025Differentiable Quadratic Optimization For the Maximum Independent Set Problem
  33. ICML 2025Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
  34. ICML 2025Dimension-Free Adaptive Subgradient Methods with Frequent Directions
  35. ICML 2025Discrepancy Minimization in Input-Sparsity Time
  36. ICML 2025Distributed Conformal Prediction via Message Passing
  37. ICML 2025Distributed Event-Based Learning via ADMM
  38. ICML 2025Dueling Convex Optimization with General Preferences
  39. ICML 2025Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization
  40. ICML 2025Efficient Distributed Optimization under Heavy-Tailed Noise
  41. ICML 2025Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
  42. ICML 2025Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
  43. ICML 2025End-to-End Learning Framework for Solving Non-Markovian Optimal Control
  44. ICML 2025Enforcing Idempotency in Neural Networks
  45. ICML 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinement
  46. ICML 2025Ensemble Learned Bloom Filters: Two Oracles are Better than One
  47. ICML 2025Exact risk curves of signSGD in High-Dimensions: quantifying preconditioning and noise-compression effects
  48. ICML 2025Expected Variational Inequalities
  49. ICML 2025Exploiting Curvature in Online Convex Optimization with Delayed Feedback
  50. ICML 2025Exploiting Similarity for Computation and Communication-Efficient Decentralized 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