More Like this

1. Learning Proximal Operators with Gaussian Process and Adaptive Quantization in Distributed Optimization

   https://doi.org/10.31390/gradschool_dissertations.6484  

   Duarte, Aldo (May 2024, LSU Doctoral Dissertations)

   In networks consisting of agents communicating with a central coordinator and working together to solve a global optimization problem in a distributed manner, the agents are often required to solve private proximal minimization subproblems. Such a setting often requires a further decomposition method to solve the global distributed problem, resulting in extensive communication overhead. In networks where communication is expensive, it is crucial to reduce the communication overhead of the distributed optimization scheme. Integrating Gaussian processes (GP) as a learning component to the Alternating Direction Method of Multipliers (ADMM) has proven effective in learning each agent's local proximal operator to reduce the required communication exchange. In this work, we propose to combine this learning method with adaptive uniform quantization in a hybrid approach that can achieve further communication reduction when solving a distributed optimization problem with ADMM. This adaptive quantization first considers setting the mid-value and window length according to the mean and covariance given by GP. In a later stage of our study, this adaptation is extended to also consider the variation of the quantization bit resolution. In addition, a convergence analysis of this setting is derived, leading to convergence conditions and error bounds in the cases where convergence cannot be formally proven. Furthermore, we study the impact of the communication decision-making of the coordinator, leading to the proposition of several query strategies using the agent's uncertainty measures given by the regression process. Extensive numerical experiments of a distributed sharing problem with quadratic cost functions for the agents have been conducted throughout this study. The results have demonstrated that the various algorithms proposed have successfully achieved their primary goal of minimizing the overall communication overhead while ensuring that the global solutions maintain satisfactory levels of accuracy. The favorable accuracy observed in the numerical experiments is consistent with the findings of the derived convergence analysis. In instances where convergence proof is lacking, we have shown that the overall ADMM residual remains bounded by a diminishing threshold. This implies that we can anticipate our algorithmic solutions to closely approximate the actual solution, thus validating the reliability of our approaches. 

   more » « less
2. Optimal querying for communication-efficient ADMM using Gaussian process regression

   https://doi.org/10.1016/j.fraope.2024.100080  

   Duarte, Aldo; Nghiem, Truong X; Wei, Shuangqing (March 2024, Franklin Open)

   In distributed optimization schemes consisting of a group of agents connected to a central coordinator, the optimization algorithm often involves the agents solving private local sub-problems and exchanging data frequently with the coordinator to solve the global distributed problem. In those cases, the query-response mechanism usually causes excessive communication costs to the system, necessitating communication reduction in scenarios where communication is costly. Integrating Gaussian processes (GP) as a learning component to the Alternating Direction Method of Multipliers (ADMM) has proven effective in learning each agent’s local proximal operator to reduce the required communication exchange. A key element for integrating GP into the ADMM algorithm is the querying mechanism upon which the coordinator decides when communication with an agent is required. In this paper, we formulate a general querying decision framework as an optimization problem that balances reducing the communication cost and decreasing the prediction error. Under this framework, we propose a joint query strategy that takes into account the joint statistics of the query and ADMM variables and the total communication cost of all agents in the presence of uncertainty caused by the GP regression. In addition, we derive three different decision mechanisms that simplify the general framework by making the communication decision for each agent individually. We integrate multiple measures to quantify the trade-off between the communication cost reduction and the optimization solution’s accuracy/optimality. The proposed methods can achieve significant communication reduction and good optimization solution accuracy for distributed optimization, as demonstrated by extensive simulations of a distributed sharing problem. 

   more » « less
3. PrivOpt: an intrinsically private distributed optimization algorithm

   https://doi.org/10.23919/ACC53348.2022.9867222  

   Esteki, Amir-Salar; Kia, Solmaz S. (June 2022, 2022 American Control Conference (ACC))

   A critical factor for expanding the adoption of networked solutions is ensuring local data privacy of in-network agents implementing a distributed algorithm. In this paper, we consider privacy preservation in the distributed optimization problem in the sense that local cost parameters should not be revealed. Current approaches to privacy preservation normally propose methods that sacrifice exact convergence or increase communication overhead. We propose PrivOpt, an intrinsically private distributed optimization algorithm that converges exponentially fast without any convergence error or using extra communication channels. We show that when the number of the parameters of the local cost is greater than the dimension of the decision variable of the problem, no malicious agent, even if it has access to all transmitted-in and -out messages in the network, can obtain local cost parameters of other agents. As an application study, we show how our proposed PrivOpt algorithm can be used to solve an optimal resource allocation problem with the guarantees that the local cost parameters of all the agents stay private. 

   more » « less
4. Distributed Multi-Agent Bayesian Optimization for Unknown Design Space Exploration

   https://doi.org/10.1115/DETC2024-143377  

   Chen, Siyu; Bayrak, Alparslan Emrah; Sha, Zhenghui (August 2024, American Society of Mechanical Engineers)

   In multi-agent Bayesian optimization for Design Space Exploration (DSE), identifying a communication network among agents to share useful design information for enhanced cooperation and performance, considering the trade-off between connectivity and cost, poses significant challenges. To address this challenge, we develop a distributed multi-agent Bayesian optimization (DMABO) framework and study how communication network structures/connectivity and the resulting cost would impact the performance of a team of agents when finding the global optimum. Specifically, we utilize Lloyd’s algorithm to partition the design space to assign distinct regions to individual agents for exploration in the distributed multi-agent system (MAS). Based on this partitioning, we generate communication networks among agents using two models: 1) a range-limited model of communication constrained by neighborhood information; and 2) a range-free model without neighborhood constraints. We introduce network density as a metric to quantify communication costs. Then, we generate communication networks by gradually increasing the network density to assess the impact of communication costs on the performance of MAS in DSE. The experimental results show that the communication network based on the range-limited model can significantly improve performance without incurring high communication costs. This indicates that increasing the density of a communication network does not necessarily improve MAS performance in DSE. Furthermore, the results indicate that communication is only beneficial for team performance if it occurs between specific agents whose search regions are critically relevant to the location of the global optimum. The proposed DMABO framework and the insights obtained can help identify the best trade-off between communication structure and cost for MAS in unknown design space exploration. 

   more » « less
5. Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

   https://doi.org/10.24963/ijcai.2021/202  

   Hu, Rui; Gong, Yanmin; Guo, Yuanxiong (August 2021, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence)

   Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee. Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost. We rigorously analyze the convergence of our approach and utilize Renyi DP to tightly account the end-to-end DP guarantee. Extensive experiments on benchmark datasets validate that our approach outperforms previous differentially-private FL approaches in both privacy guarantee and communication efficiency. 

   more » « less