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 19 / 38 页

  1. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
  2. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
  3. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
  4. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
  5. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
  6. ICML 2025Robust Sparsification via Sensitivity
  7. ICML 2025ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
  8. ICML 2025Safe-EF: Error Feedback for Non-smooth Constrained Optimization
  9. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
  10. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
  11. ICML 2025Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
  12. ICML 2025Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
  13. ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
  14. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
  15. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
  16. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
  17. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
  18. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  19. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
  20. ICML 2025SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
  21. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
  22. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
  23. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  24. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
  25. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions
  26. ICML 2025The Empirical Mean is Minimax Optimal for Local Glivenko-Cantelli
  27. ICML 2025The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations
  28. ICML 2025The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
  29. ICML 2025Tilted Sharpness-Aware Minimization
  30. ICML 2025Toward a Unified Theory of Gradient Descent under Generalized Smoothness
  31. ICML 2025Towards a Formal Theory of Representational Compositionality
  32. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
  33. ICML 2025Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints
  34. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
  35. ICML 2025When to Forget? Complexity Trade-offs in Machine Unlearning
  36. ICML 2025Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
  37. NeurIPS 20253BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
  38. NeurIPS 2025A Beyond-Worst-Case Analysis of Greedy k-means++
  39. NeurIPS 2025A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems
  40. NeurIPS 2025A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning
  41. NeurIPS 2025A Geometric Analysis of PCA
  42. NeurIPS 2025A Gradient Guided Diffusion Framework for Chance Constrained Programming
  43. NeurIPS 2025A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows
  44. NeurIPS 2025A Minimalist Example of Edge-of-Stability and Progressive Sharpening
  45. NeurIPS 2025A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
  46. NeurIPS 2025A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees
  47. NeurIPS 2025A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization
  48. NeurIPS 2025A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation
  49. NeurIPS 2025A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics
  50. NeurIPS 2025A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models

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