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 463 篇，第 7 / 10 页

  1. ICML 2025MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
  2. ICML 2025Modular Duality in Deep Learning
  3. ICML 2025Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning
  4. ICML 2025Multiobjective distribution matching
  5. ICML 2025Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
  6. ICML 2025Nonconvex Theory of $M$-estimators with Decomposable Regularizers
  7. ICML 2025Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
  8. ICML 2025On Differential Privacy for Adaptively Solving Search Problems via Sketching
  9. ICML 2025On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
  10. ICML 2025On the Local Complexity of Linear Regions in Deep ReLU Networks
  11. ICML 2025Online Conformal Prediction via Online Optimization
  12. ICML 2025Optimal Decision Tree Pruning Revisited: Algorithms and Complexity
  13. ICML 2025Optimization for Neural Operators can Benefit from Width
  14. ICML 2025Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees
  15. ICML 2025OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
  16. ICML 2025PARQ: Piecewise-Affine Regularized Quantization
  17. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
  18. ICML 2025Policy Optimization for CMDPs with Bandit Feedback: Learning Stochastic and Adversarial Constraints
  19. ICML 2025Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems
  20. ICML 2025Position: A Theory of Deep Learning Must Include Compositional Sparsity
  21. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
  22. ICML 2025Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
  23. ICML 2025Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
  24. ICML 2025Principled Algorithms for Optimizing Generalized Metrics in Binary Classification
  25. ICML 2025Procurement Auctions via Approximately Optimal Submodular Optimization
  26. ICML 2025Radio: Rate–Distortion Optimization for Large Language Model Compression
  27. ICML 2025Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization
  28. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
  29. ICML 2025Retraining with Predicted Hard Labels Provably Increases Model Accuracy
  30. ICML 2025Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
  31. ICML 2025Robust Sparsification via Sensitivity
  32. ICML 2025ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
  33. ICML 2025Safe-EF: Error Feedback for Non-smooth Constrained Optimization
  34. ICML 2025Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
  35. ICML 2025Scalable Meta-Learning via Mixed-Mode Differentiation
  36. ICML 2025Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
  37. ICML 2025Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers
  38. ICML 2025SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming
  39. ICML 2025SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning
  40. ICML 2025SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization
  41. ICML 2025Sharp Optimality of Simple, Plug-in Estimation of the Fisher Information of a Smoothed Density
  42. ICML 2025Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
  43. ICML 2025Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
  44. ICML 2025Sparse-pivot: Dynamic correlation clustering for node insertions
  45. ICML 2025SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models
  46. ICML 2025Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
  47. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
  48. ICML 2025Structured Preconditioners in Adaptive Optimization: A Unified Analysis
  49. ICML 2025Subspace Optimization for Large Language Models with Convergence Guarantees
  50. ICML 2025The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions

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