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 4 / 38 页

  1. ICLR 2026Machine Unlearning under Retain–Forget Entanglement
  2. ICLR 2026MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization
  3. ICLR 2026MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP Problems
  4. ICLR 2026Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
  5. ICLR 2026Monotone Near-Zero-Sum Games: A Generalization of Convex-Concave Minimax
  6. ICLR 2026MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates
  7. ICLR 2026Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies
  8. ICLR 2026Muon Outperforms Adam in Tail-End Associative Memory Learning
  9. ICLR 2026MuonBP: Faster Muon via Block-Periodic Orthogonalization
  10. ICLR 2026Nearly Space-Optimal Graph and Hypergraph Sparsification in Insertion-Only Data Streams
  11. ICLR 2026Nesterov Finds GRAAL: Optimal and Adaptive Gradient Method for Convex Optimization
  12. ICLR 2026Neural Collapse in Multi-Task Learning
  13. ICLR 2026Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
  14. ICLR 2026Neural Multi-Objective Combinatorial Optimization for Flexible Job Shop Scheduling Problems
  15. ICLR 2026Never Saddle: Reparameterized Steepest Descent as Mirror Flow
  16. ICLR 2026Newton Method Revisited: Global Convergence Rates up to $O(1/k^3)$ for Stepsize Schedules and Linesearch Procedures
  17. ICLR 2026Non-Asymptotic Analysis of Efficiency in Conformalized Regression
  18. ICLR 2026Non-Convex Federated Optimization under Cost-Aware Client Selection
  19. ICLR 2026On Smoothness Bounds for Non-Clairvoyant Scheduling with Predictions
  20. ICLR 2026On the $O(1/T)$ Convergence of Alternating Gradient Descent–Ascent in Bilinear Games
  21. ICLR 2026On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
  22. ICLR 2026On the Convergence Behavior of Preconditioned Gradient Descent Toward the Rich Learning Regime
  23. ICLR 2026On the Convergence Direction of Gradient Descent
  24. ICLR 2026On the Convergence of Two-Layer Kolmogorov-Arnold Networks with First-Layer Training
  25. ICLR 2026On The Surprising Effectiveness of a Single Global Merging in Decentralized Learning
  26. ICLR 2026On Universality of Deep Equivariant Networks
  27. ICLR 2026Online Decision-Focused Learning
  28. ICLR 2026Online Inventory Optimization in Non-Stationary Environment
  29. ICLR 2026Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
  30. ICLR 2026Operator Theory-Driven Autoformulation of MDPs for Control of Queueing Systems
  31. ICLR 2026OR-PRM: A Process Reward Model for Algorithmic Problem in Operations Research
  32. ICLR 2026Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
  33. ICLR 2026Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
  34. ICLR 2026Predictive Differential Training Guided by Training Dynamics
  35. ICLR 2026Provably Accelerated Imaging with Restarted Inertia and Score-based Image Priors
  36. ICLR 2026Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction
  37. ICLR 2026PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
  38. ICLR 2026Quasi-Equivariant Metanetworks
  39. ICLR 2026RADAR: Learning to Route with Asymmetry-aware Distance Representations
  40. ICLR 2026Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction
  41. ICLR 2026Reducing Contextual Stochastic Bilevel Optimization via Structured Function Approximation
  42. ICLR 2026Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
  43. ICLR 2026RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States
  44. ICLR 2026Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training
  45. ICLR 2026Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
  46. ICLR 2026Riemannian Federated Learning via Averaging Gradient Streams
  47. ICLR 2026Riemannian Zeroth-Order Gradient Estimation with Structure-Preserving Metrics for Geodesically Incomplete Manifolds
  48. ICLR 2026Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
  49. ICLR 2026Robust Training of Neural Networks at Arbitrary Precision and Sparsity
  50. ICLR 2026Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures

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