Imagen de Portada

Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gao, Wenzhi, Sun, Chunlin, Xue, Chenyu, Ge, Dongdong, Ye, Yinyu
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond $\mathcal{O}(\sqrt{T})$ Regret: Decoupling Learning and Decision-making in Online Linear Programming
por: Gao, Wenzhi, et al.
Publicado: (2025)

Solving Linear Programs with Fast Online Learning Algorithms
por: Gao, Wenzhi, et al.
Publicado: (2021)

Wait-Less Offline Tuning and Re-solving for Online Decision Making
por: Sun, Jingruo, et al.
Publicado: (2024)

A Homogeneous Second-Order Descent Method for Nonconvex Optimization
por: Zhang, Chuwen, et al.
Publicado: (2022)

PDHCG: A Scalable First-Order Method for Large-Scale Competitive Market Equilibrium Computation
por: Liu, Huikang, et al.
Publicado: (2025)

A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes
por: Lin, Zhenwei, et al.
Publicado: (2024)

Gradient Methods with Online Scaling
por: Gao, Wenzhi, et al.
Publicado: (2024)

An Enhanced ADMM-based Interior Point Method for Linear and Conic Optimization
por: Deng, Qi, et al.
Publicado: (2022)

Gradient Methods with Online Scaling Part I. Theoretical Foundations
por: Gao, Wenzhi, et al.
Publicado: (2025)

Gradient Methods with Online Scaling Part II. Practical Aspects
por: Chu, Ya-Chi, et al.
Publicado: (2025)

When Does Primal Interior Point Method Beat Primal-dual in Linear Optimization?
por: Gao, Wenzhi, et al.
Publicado: (2024)

Homogeneous Second-Order Descent Framework: A Fast Alternative to Newton-Type Methods
por: He, Chang, et al.
Publicado: (2023)

Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
por: Chen, Yanguang, et al.
Publicado: (2023)

A Homogenization Approach for Gradient-Dominated Stochastic Optimization
por: Tan, Jiyuan, et al.
Publicado: (2023)

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
por: Chu, Ya-Chi, et al.
Publicado: (2025)

A Practical GPU-Enhanced Matrix-Free Primal-Dual Method for Large-Scale Conic Programs
por: Lin, Zhenwei, et al.
Publicado: (2025)

A Technical Note on the Implementation and Use of PDCS
por: Lin, Zhenwei, et al.
Publicado: (2026)

Learning to Pivot as a Smart Expert
por: Liu, Tianhao, et al.
Publicado: (2023)

Beyond Nonconvexity: A Universal Trust-Region Method with New Analyses
por: Jiang, Yuntian, et al.
Publicado: (2023)

Trust Region Methods For Nonconvex Stochastic Optimization Beyond Lipschitz Smoothness
por: Xie, Chenghan, et al.
Publicado: (2023)

Restarted Primal-Dual Hybrid Conjugate Gradient Method for Large-Scale Quadratic Programming
por: Huang, Yicheng, et al.
Publicado: (2024)

Scalable Approximate Optimal Diagonal Preconditioning
por: Gao, Wenzhi, et al.
Publicado: (2023)

PDHCG-II: An Enhanced Version of PDHCG for Large-Scale Convex QP
por: Li, Hongpei, et al.
Publicado: (2026)

From an Interior Point to a Corner Point: Smart Crossover
por: Ge, Dongdong, et al.
Publicado: (2021)

A Safe First-Order Method for Pricing-Based Resource Allocation in Safety-Critical Networks
por: Turan, Berkay, et al.
Publicado: (2023)

Achieving Instance-dependent Sample Complexity for Constrained Markov Decision Process
por: Jiang, Jiashuo, et al.
Publicado: (2024)

Cardinal Optimizer (COPT) User Guide
por: Ge, Dongdong, et al.
Publicado: (2022)

Accelerating Low-Rank Factorization-Based Semidefinite Programming Algorithms on GPU
por: Han, Qiushi, et al.
Publicado: (2024)

D-PDLP: Scaling PDLP to Distributed Multi-GPU Systems
por: Li, Hongpei, et al.
Publicado: (2026)

Online Linear Programming with Batching
por: Xu, Haoran, et al.
Publicado: (2024)

The Second-Order Tâtonnement: Decentralized Interior-Point Methods for Market Equilibrium
por: Zhang, Chuwen, et al.
Publicado: (2025)

Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization
por: Su, Yuexin, et al.
Publicado: (2026)

A Low-Rank ADMM Splitting Approach for Semidefinite Programming
por: Han, Qiushi, et al.
Publicado: (2024)

Byzantine-Resilient Decentralized Online Resource Allocation
por: Wang, Runhua, et al.
Publicado: (2025)

Accelerating Trust-Region Methods: An Attempt to Balance Global and Local Efficiency
por: Jiang, Yuntian, et al.
Publicado: (2025)

FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming
por: Li, Hongpei, et al.
Publicado: (2025)

OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training
por: Li, Hongpei, et al.
Publicado: (2025)

On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape
por: Qin, Lei, et al.
Publicado: (2025)

cuPDLP-C: A Strengthened Implementation of cuPDLP for Linear Programming by C language
por: Lu, Haihao, et al.
Publicado: (2023)

Online Allocation of Throughput-Constrained Resources Using Proxy Assignments
por: Hssaine, Chamsi, et al.
Publicado: (2024)