Prashant Khanduri

Prashant Khanduri

Auto-generated profile, based on publicly available information

Prashant Khanduri

Wayne State University

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
YZYihua Zhang
Yihua Zhang
PKPrashant Khanduri
Prashant Khanduri
ITIoannis Tsaknakis
Ioannis Tsaknakis
YYYuguang Yao
Yuguang Yao
MHMingyi Hong
Mingyi Hong
SLSijia Liu
Sijia Liu
Recently, bilevel optimization (BLO) has taken center stage in some very exciting developments in the area of signal processing (SP) and machine learning (ML). Roughly speaking, BLO is a classical optimization problem that involves two levels of hierarchy (i.e., upper and lower levels), wherein obtaining the solution to the upper-level problem requires solving the lower-level one. BLO has become popular largely because it is powerful in modeling problems in SP and ML, among others, that involve optimizing nested objective functions. Prominent applications of BLO range from resource allocation for wireless systems to adversarial ML. In this work, we focus on a class of tractable BLO problems that often appear in SP and ML applications. We provide an overview of some basic concepts of this class of BLO problems, such as their optimality conditions, standard algorithms (including their optimization principles and practical implementations) as well as how they can be leveraged to obtain state-of-the-art results for several key SP and ML applications. Further, we discuss some recent advances in BLO theory and its implications for applications, and we point out some limitations of the state of the art that require significant future research efforts. We hope that this article, together with the associated open source BLO toolbox we developed for algorithm benchmarking, can serve to accelerate the adoption of BLO as a generic tool to model, analyze, and innovate on a wide array of emerging SP and ML applications.

2 December 2024
Verified
Conference Paper
Open access
MFMinghong Fang
Minghong Fang
ZZZifan Zhang
Zifan Zhang
HAHairi
Hairi
PKPrashant Khanduri
Prashant Khanduri
JLJia Liu
Jia Liu
NGNeil Gong
Neil Gong
Federated learning (FL) enables multiple clients to collaboratively train machine learning models without revealing their private training data. In conventional FL, the system follows the server-assisted architecture (server-assisted FL), where the training process is coordinated by a central server. However, the server-assisted FL framework suffers from poor scalability due to a communication bottleneck at the server, and trust dependency issues. To address challenges, decentralized federated learning (DFL) architecture has been proposed to allow clients to train models collaboratively in a serverless and peer-to-peer manner. However, due to its fully decentralized nature, DFL is highly vulnerable to poisoning attacks, where malicious clients could manipulate the system by sending carefully-crafted local models to their neighboring clients. To date, only a limited number of Byzantine-robust DFL methods have been proposed, most of which are either communication-inefficient or remain vulnerable to advanced poisoning attacks. In this paper, we propose a new algorithm called BALANCE (Byzantine-robust averaging through local similarity in decentralization) to defend against poisoning attacks in DFL. In BALANCE, each client leverages its own local model as a similarity reference to determine if the received model is malicious or benign. We establish the theoretical convergence guarantee for BALANCE under poisoning attacks in both strongly convex and non-convex settings. Furthermore, the convergence rate of BALANCE under poisoning attacks matches those of the state-of-the-art counterparts in Byzantine-free settings. Extensive experiments also demonstrate that BALANCE outperforms existing DFL methods and effectively defends against poisoning attacks.

24 September 2021 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
XCXiancheng Cheng
Xiancheng Cheng
PKPrashant Khanduri
Prashant Khanduri
BCBaixiao Chen
Baixiao Chen
PVPramod K. Varshney
Pramod K. Varshney
In this work, we propose a joint collaboration-compression framework for sequential estimation of a random vector parameter in a resource constrained wireless sensor network (WSN). Specifically, we propose a framework where the local sensors first collaborate (via a collaboration matrix) with each other. Then a subset of sensors selected to communicate with the FC linearly compress their observations before transmission. We design near-optimal collaboration and linear compression strategies under power constraints via alternating minimization of the sequential minimum mean square error. The objective function for collaboration design is generally non-convex. We establish correspondence between the sparse collaboration matrix and the non-sparse vector consisting of the nonzero elements of the collaboration matrix. Then, we reformulate and solve the collaboration design problem using quadratically constrained quadratic program (QCQP). The compression design problem is solved using the same methodology. We propose two versions of compression design, one centralized scheme where the compression strategies are derived at the FC and decentralized, where the local sensors compute their individual compression strategies independently. Importantly, we show that the proposed methods can also be used for estimating time-varying random vector parameters. Finally, numerical results are provided to demonstrate the effectiveness of the proposed framework.

19 November 2021 in IEEE Transactions on Signal and Information Processing over Networks
Verified
Journal Article
Closed access
SBSaikiran Bulusu
Saikiran Bulusu
PKPrashant Khanduri
Prashant Khanduri
SKSwatantra Kafle
Swatantra Kafle
PSPranay Sharma
Pranay Sharma
PVPramod K. Varshney
Pramod K. Varshney
Distributed learning is an important paradigm in the current machine learning algorithms with large datasets. In this paper, distributed stochastic optimization problem of minimizing a nonconvex function in an adversarial setting is considered. A robust variant of the stochastic variance-reduced algorithm is proposed. In the distributed setup, we assume that a fraction of worker nodes (WNs) can be Byzantines. We assume that the batch gradients are computed at the WNs and the stochastic gradients are computed at the central node (CN). We provide the convergence rate of the proposed algorithm which employs the design of a novel filtering rule that is independent of the problem dimension. Furthermore, we capture the effect of Byzantines present in the network on the convergence performance of the algorithm. We evaluate the performance of the proposed algorithm and present the simulation results using real world datasets, in addition to providing the theoretical guarantees.

5 August 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XCXiancheng Cheng
Xiancheng Cheng
BGBaocheng Geng
Baocheng Geng
PKPrashant Khanduri
Prashant Khanduri
BCBaixiao Chen
Baixiao Chen
PVPramod K. Varshney
Pramod K. Varshney
In this work, we propose a joint collaboration-compression framework for the random signal detection problem in a resource constrained wireless sensor network (WSN). Specifically, we propose a framework where the local sensors first collaborate (via a linear collaboration matrix) with each other. Then a subset of sensors linearly compress their aggregated information before communicating with the fusion center (FC). We propose a novel metric called generalized deflection coefficient (GDC) for evaluating the detection performance which is shown to be tightly upper bounded by the Kullback-Leibler divergence for Gaussian observations. We jointly design the linear collaboration and compression strategies under power constraints via alternating maximization of the proposed GDC metric. Finally, numerical results are provided to demonstrate the effectiveness of the proposed framework.

2 December 2024
Verified
Book Chapter
Closed access
PDF file
YQYao Qiang
Yao Qiang
CLChengyin Li
Chengyin Li
PKPrashant Khanduri
Prashant Khanduri
DZDongxiao Zhu
Dongxiao Zhu