首页/论文/2004.01305

arXiv 2004.013052020-04-02stat.MLcs.LG

Distributed Primal-Dual Optimization for Online Multi-Task Learning

Baidu Research（百度研究院）

Peng Yang, Ping Li

英文摘要：

Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task relatedness. To address these issues, in this paper we consider a setting where multiple tasks are geographically located in different places, where one task can synchronize data with others to leverage knowledge of related tasks. Specifically, we propose an adaptive primal-dual algorithm, which not only captures task-specific noise in adversarial learning but also carries out a projection-free update with runtime efficiency. Moreover, our model is well-suited to decentralized periodic-connected tasks as it allows the energy-starved or bandwidth-constraint tasks to postpone the update. Theoretical results demonstrate the convergence guarantee of our distributed algorithm with an optimal regret. Empirical results confirm that the proposed model is highly effective on various real-world datasets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Straggler-Agnostic and Communication-Efficient Distributed Primal-Dual Algorithm for High-Dimensional Data Mining

University of Pittsburgh（匹兹堡大学）

Recently, reducing communication time between machines becomes the main focus of distributed data mining. Previous methods propose to make workers do more computation locally before aggregating local solutions in the server such that fewer communication rounds between server and workers are required. However, these methods do not consider reducing the communication time per round and work very poor under certain conditions, for example, when there are straggler problems or the dataset is of high dimension. In this paper, we target to reduce communication time per round as well as the required …

2019-10-09cs.LGstat.ML

NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization

Iowa State University（爱荷华州立大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Princeton University（普林斯顿大学）

We study a stochastic and distributed algorithm for nonconvex problems whose objective consists of a sum of $N$ nonconvex $L_i/N$-smooth functions, plus a nonsmooth regularizer. The proposed NonconvEx primal-dual SpliTTing (NESTT) algorithm splits the problem into $N$ subproblems, and utilizes an augmented Lagrangian based primal-dual scheme to solve it in a distributed and stochastic manner. With a special non-uniform sampling, a version of NESTT achieves $ε$-stationary solution using $\mathcal{O}((\sum_{i=1}^N\sqrt{L_i/N})^2/ε)$ gradient evaluations, which can be up to $\mathcal{O}(N)$ times…

2016-11-07cs.LGmath.OCstat.ML

Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps

Argonne National Laboratory（阿贡国家实验室）；Wayne State University（韦恩州立大学）

In distributed machine learning, efficient training across multiple agents with different data distributions poses significant challenges. Even with a centralized coordinator, current algorithms that achieve optimal communication complexity typically require either large minibatches or compromise on gradient complexity. In this work, we tackle both centralized and decentralized settings across strongly convex, convex, and nonconvex objectives. We first demonstrate that a basic primal-dual method, (Accelerated) Gradient Ascent Multiple Stochastic Gradient Descent (GA-MSGD), applied to the Lagra…

2024-08-11cs.DCcs.LGmath.OC

Large Scale Model Predictive Control with Neural Networks and Primal Active Sets

University of Pennsylvania（宾夕法尼亚大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）

This work presents an explicit-implicit procedure to compute a model predictive control (MPC) law with guarantees on recursive feasibility and asymptotic stability. The approach combines an offline-trained fully-connected neural network with an online primal active set solver. The neural network provides a control input initialization while the primal active set method ensures recursive feasibility and asymptotic stability. The neural network is trained with a primal-dual loss function, aiming to generate control sequences that are primal feasible and meet a desired level of suboptimality. Sin…

2021-07-05cs.LGcs.SYeess.SY

A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization

National University of Singapore（新加坡国立大学）；Wisconsin Institute for Discovery（威斯康星发现研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

We propose a communication- and computation-efficient distributed optimization algorithm using second-order information for solving empirical risk minimization (ERM) problems with a nonsmooth regularization term. Our algorithm is applicable to both the primal and the dual ERM problem. Current second-order and quasi-Newton methods for this problem either do not work well in the distributed setting or work only for specific regularizers. Our algorithm uses successive quadratic approximations of the smooth part, and we describe how to maintain an approximation of the (generalized) Hessian and sol…

2019-12-12cs.LGmath.OCstat.ML

DSCOVR: Randomized Primal-Dual Block Coordinate Algorithms for Asynchronous Distributed Optimization

Machine learning with big data often involves large optimization models. For distributed optimization over a cluster of machines, frequent communication and synchronization of all model parameters (optimization variables) can be very costly. A promising solution is to use parameter servers to store different subsets of the model parameters, and update them asynchronously at different machines using local datasets. In this paper, we focus on distributed optimization of large linear models with convex loss functions, and propose a family of randomized primal-dual block coordinate algorithms that…

2017-10-13math.OCstat.ML

更多相关论文收起更多论文

在线约束优化推断：对偶最优性与序列二次规划

Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming

本文提出了一种全新的在线序列二次规划方法，用于解决具有等式和不等式约束的随机优化问题，实现了对偶渐近最小最大最优性，无需投影运算。

2025-11-27cs.LGmath.OCmath.ST

松弛全局几何下分布式优化的量化随机原始-对偶方法

Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry

Indian Institute of Technology Bombay（印度理工学院班加罗尔）；Tata Consultancy Services Research（塔塔咨询公司研究）

提出量化随机原始-对偶方法q-PDGD，在松弛全局几何下证明线性收敛到邻域或O(1/k)收敛，匹配最优集中随机复杂度。

2026-06-11cs.AIcs.LGcs.SY

关于CoCoA与ADMM在分布式经验风险最小化中的关系

On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization

Department of Industrial & Systems Engineering, University of Wisconsin–Madison（工业与系统工程系，威斯康星大学麦迪逊分校）

本文从统一原始-对偶视角揭示CoCoA与ADMM两类分布式ERM算法的内在联系，证明岭正则化下CoCoA等价于特定近端ADMM方案，并给出ADMM型方法的统一收敛分析和早停准则。

2026-06-28cs.LGmath.OCstat.ML

Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss

University of Michigan（密歇根大学）；University of Southern California（南加州大学）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the episodes, and both the loss received and the budget consumption are revealed at the end of each episode. Previous works solve this problem under the restrictive assumption that the transition model of the Markov decision processes (MDPs) is known a priori and establish regret bounds that depend polynomially on the cardinalities of the state space $\mathcal{S}$ an…

2021-10-18cs.LGmath.OCstat.ML

Online Adaptive Machine Learning Based Algorithm for Implied Volatility Surface Modeling

Northwestern University（西北大学）

In this work, we design a machine learning based method, online adaptive primal support vector regression (SVR), to model the implied volatility surface (IVS). The algorithm proposed is the first derivation and implementation of an online primal kernel SVR. It features enhancements that allow efficient online adaptive learning by embedding the idea of local fitness and budget maintenance to dynamically update support vectors upon pattern drifts. For algorithm acceleration, we implement its most computationally intensive parts in a Field Programmable Gate Arrays hardware, where a 132x speedup o…

2018-06-07cs.LGq-fin.CPstat.ML

An Online Algorithm for Chance Constrained Resource Allocation

Cainiao Network（菜鸟网络）

This paper studies the online stochastic resource allocation problem (RAP) with chance constraints. The online RAP is a 0-1 integer linear programming problem where the resource consumption coefficients are revealed column by column along with the corresponding revenue coefficients. When a column is revealed, the corresponding decision variables are determined instantaneously without future information. Moreover, in online applications, the resource consumption coefficients are often obtained by prediction. To model their uncertainties, we take the chance constraints into the consideration. To…

2023-03-06cs.LGmath.OCstat.ML

Safe and Near-Optimal Policy Learning for Model Predictive Control using Primal-Dual Neural Networks

UC Berkeley（加州大学伯克利分校）

In this paper, we propose a novel framework for approximating the explicit MPC law for linear parameter-varying systems using supervised learning. In contrast to most existing approaches, we not only learn the control policy, but also a "certificate policy", that allows us to estimate the sub-optimality of the learned control policy online, during execution-time. We learn both these policies from data using supervised learning techniques, and also provide a randomized method that allows us to guarantee the quality of each learned policy, measured in terms of feasibility and optimality. This in…

2019-06-19cs.LGcs.SYeess.SY

Decentralized Feature-Distributed Optimization for Generalized Linear Models

We consider the "all-for-one" decentralized learning problem for generalized linear models. The features of each sample are partitioned among several collaborating agents in a connected network, but only one agent observes the response variables. To solve the regularized empirical risk minimization in this distributed setting, we apply the Chambolle--Pock primal--dual algorithm to an equivalent saddle-point formulation of the problem. The primal and dual iterations are either in closed-form or reduce to coordinate-wise minimization of scalar convex functions. We establish convergence rates for…

2021-10-28cs.MAmath.OCstat.ML

Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning

Princeton University（普林斯顿大学）

We study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a few coordinates of the value and policy estimates as a new state transition is observed. These methods use small storage and has low computational complexity per iteration. The SPD methods find an absolute-$ε$-optimal policy, with high probability, using $\mathcal{O}\left(\frac{|\mathcal{S}|^4 |\mathcal{A}|^2σ^2 }{(1-γ)^6ε^2} \right)$ iterations/samples for th…

2016-12-08cs.AImath.OCstat.ML