深度学习 · optimization论文趋势 2023–2026

主要结论

• 深度学习 · optimization论文从 2023 年的 256 篇降到 2026 年的 240 篇，热度在回落。
• NeurIPS 是发深度学习 · optimization论文最多的会议，2023–2026 年共 500 篇，占四个会议总量的 52%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 23 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 6；同组增长最快的扩散模型是 4.1 倍，深度学习 · optimization是 0.9 倍。

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

• NeurIPS 2026Achieving Directional-Stationarity from a Single Random Direction Step
• ICML 2026Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
• ICLR 2026From Sorting Algorithms to Scalable Kernels: Bayesian Optimization in High-Dimensional Permutation Spaces
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
• ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
• ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
• CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
• NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
• ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization
• NeurIPS 2023$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
• ICML 2023Buying Information for Stochastic Optimization
• ICLR 2023Alternating Differentiation for Optimization Layers
• CVPR 2023Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization
• NeurIPS 2026Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
• ICML 2026Riemannian Optimization for Fair Spectral Clustering
• ICLR 2026Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective
• CVPR 2026Its Never Too Late Noise Optimization for Collapse Recovery in

全部深度学习 · optimization论文

共 953 篇，第 17 / 20 页

801. ICML 2023Supported Trust Region Optimization for Offline Reinforcement Learning
802. ICML 2023SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems
803. ICML 2023Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction
804. ICML 2023Target-based Surrogates for Stochastic Optimization
805. ICML 2023Towards Practical Preferential Bayesian Optimization with Skew Gaussian Processes
806. ICML 2023Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP Solver
807. ICML 2023Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization
808. ICML 2023Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy
809. ICML 2023User-level Private Stochastic Convex Optimization with Optimal Rates
810. NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
811. NeurIPS 2023$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
812. NeurIPS 2023A Computationally Efficient Sparsified Online Newton Method
813. NeurIPS 2023A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability
814. NeurIPS 2023A Guide Through the Zoo of Biased SGD
815. NeurIPS 2023A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
816. NeurIPS 2023A Unified Approach for Maximizing Continuous DR-submodular Functions
817. NeurIPS 2023A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization
818. NeurIPS 2023Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization
819. NeurIPS 2023Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance
820. NeurIPS 2023Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization
821. NeurIPS 2023Adjustable Robust Reinforcement Learning for Online 3D Bin Packing
822. NeurIPS 2023Advancing Bayesian Optimization via Learning Correlated Latent Space
823. NeurIPS 2023Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing
824. NeurIPS 2023An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition
825. NeurIPS 2023An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits
826. NeurIPS 2023An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization
827. NeurIPS 2023Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
828. NeurIPS 2023Bayesian Optimization with Cost-varying Variable Subsets
829. NeurIPS 2023Behavior Alignment via Reward Function Optimization
830. NeurIPS 2023Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
831. NeurIPS 2023Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time
832. NeurIPS 2023Bi-Level Offline Policy Optimization with Limited Exploration
833. NeurIPS 2023Bicriteria Approximation Algorithms for the Submodular Cover Problem
834. NeurIPS 2023Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start
835. NeurIPS 2023Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training
836. NeurIPS 2023BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
837. NeurIPS 2023Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization
838. NeurIPS 2023Boosting with Tempered Exponential Measures
839. NeurIPS 2023BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
840. NeurIPS 2023Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
841. NeurIPS 2023Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
842. NeurIPS 2023Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
843. NeurIPS 2023Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning
844. NeurIPS 2023Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
845. NeurIPS 2023Contextual Stochastic Bilevel Optimization
846. NeurIPS 2023Convergence of Adam Under Relaxed Assumptions
847. NeurIPS 2023CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
848. NeurIPS 2023Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
849. NeurIPS 2023Debiasing Conditional Stochastic Optimization
850. NeurIPS 2023DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · optimization论文？

共 953 篇，按年份分别是 2023 年 256 篇、2024 年 294 篇、2025 年 163 篇、2026 年 240 篇。

NeurIPS 2026 有多少篇深度学习 · optimization论文？

NeurIPS 2026 有 103 篇深度学习 · optimization论文，上一届是 62 篇。

ICLR 2026 有多少篇深度学习 · optimization论文？

ICLR 2026 有 44 篇深度学习 · optimization论文，上一届是 51 篇。

ICML 2026 有多少篇深度学习 · optimization论文？

ICML 2026 有 86 篇深度学习 · optimization论文，上一届是 44 篇。

CVPR 2026 有多少篇深度学习 · optimization论文？

CVPR 2026 有 7 篇深度学习 · optimization论文，上一届是 6 篇。

哪个会议的深度学习 · optimization论文最多？

NeurIPS，2023–2026 年共 500 篇。