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 214 篇，第 4 / 5 页

  1. ICML 2026Provably Learning Attention with Queries
  2. ICML 2026Proximal-Based Generative Modeling for Bayesian Inverse Problems
  3. ICML 2026QuantumBoost: A lazy, yet fast, quantum algorithm for learning with weak hypotheses
  4. ICML 2026Rational Neural Networks have Expressivity Advantages
  5. ICML 2026Reducing Per-Sample Harm in Stochastic Optimization
  6. ICML 2026Refined Analysis of Entropy-Regularized Actor-Critic
  7. ICML 2026Rethinking Convergence in MoE Training: The Role of Routing Sparsity
  8. ICML 2026Rethinking Neural Network Learning Rates: A Stackelberg Perspective
  9. ICML 2026Riemannian Dueling Optimization
  10. ICML 2026Riemannian Optimization for Fair Spectral Clustering
  11. ICML 2026RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization
  12. ICML 2026Robust AI Evaluation through Maximal Lotteries
  13. ICML 2026Robust Learning via Nested Distributionally Robust Optimization
  14. ICML 2026Robust Strategic Classification under Decision-Dependent Cost Uncertainty
  15. ICML 2026Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients
  16. ICML 2026Scalable and Stable Estimation of Amari $\alpha$-Divergence using Random Fourier Features
  17. ICML 2026Scalable Kronecker-Factored Fisher Approximation for Neural Network Parameter Sensitivity
  18. ICML 2026Scaling depth capacity via zero/one-layer model expansion
  19. ICML 2026Search Space Synthesis for Parametric Functions
  20. ICML 2026Second-Order Bilevel Optimization with Accelerated Convergence Rates
  21. ICML 2026Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees
  22. ICML 2026Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
  23. ICML 2026Sharp Empirical Bernstein Inequalities for the Variance of Bounded Random Variables
  24. ICML 2026Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
  25. ICML 2026Ski Rental with Distributional Predictions of Unknown Quality
  26. ICML 2026Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective
  27. ICML 2026Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
  28. ICML 2026Solving Imperfect-Recall Games via Sum-of-Squares Optimization
  29. ICML 2026Stability Analysis of Sharpness-Aware Minimization
  30. ICML 2026Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
  31. ICML 2026Statistically Undetectable Backdoors in Deep Neural Networks
  32. ICML 2026Steady-State Behavior of Constant-Stepsize Stochastic Approximation: Gaussian Approximation and Tail Bounds
  33. ICML 2026Step-Size Stability in Stochastic Optimization: A Theoretical Perspective
  34. ICML 2026Stochastic Gradient Methods under Heavy-Tailed Noises in Weakly Convex Optimization
  35. ICML 2026Strategy-Aware Optimization Modeling with Reasoning LLMs
  36. ICML 2026Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
  37. ICML 2026Taming Stochastic Gradient Descent: Almost Sure Convergence and Saddle-Point Avoidance under $(L_{0},L_{1})$-Smoothness
  38. ICML 2026Taming the Loss Landscape of PINNs with Noisy Feynman–Kac Supervision: Operator Preconditioning and Non-Asymptotic Error Bounds
  39. ICML 2026The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
  40. ICML 2026The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
  41. ICML 2026The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
  42. ICML 2026The Optimal Sample Complexity of Linear Contracts
  43. ICML 2026The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
  44. ICML 2026The Theory and Practice of MAP Inference over Non-Convex Constraints
  45. ICML 2026The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes
  46. ICML 2026Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate
  47. ICML 2026To Grok Grokking: Provable Grokking in Ridge Regression
  48. ICML 2026Towards Atoms of Large Language Models
  49. ICML 2026Towards Fully Parameter-Free Stochastic Optimization: Grid Search with Self-Bounding Analysis
  50. ICML 2026Towards Parameter-Free Temporal Difference Learning

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