Jong-Shi Pang

About

Jong-Shi Pang is the Epstein Family Chair and Distinguished Professor of Industrial and Systems Engineering at the University of Southern California, having joined USC in August 2013. He holds a doctoral degree in Other Engineering from Stanford University, a master's degree in Statistics from Stanford University, and a bachelor's degree in Mathematics from National Taiwan University. Prior to his current appointment, he served as the Caterpillar Professor and Head of the Department of Industrial and Enterprise Systems Engineering at the University of Illinois at Urbana-Champaign, and held faculty positions at Rensselaer Polytechnic Institute, Johns Hopkins University, the University of Texas at Dallas, and Carnegie-Mellon University. His research focuses on the mathematical modeling and analysis of complex engineering and economic systems, with particular emphasis on operations research, single-agent optimization, equilibrium programming, noncooperative game theory, and constrained dynamical systems. He has made significant contributions to multi-agent optimization and equilibrium theory, receiving prestigious awards such as the John von Neumann Theory Prize and the George B. Dantzig Prize, and has been recognized as an ISI Highly Cited Researcher. He is a member of the National Academy of Engineering and a Fellow of SIAM and INFORMS. Additionally, he serves as the Editor-in-Chief of the SIAM Journal on Optimization.

Research topics

• Computer Science
• Mathematics
• Mathematical optimization
• Artificial Intelligence
• Geometry
• Algorithm
• Mathematical economics
• Combinatorics
• Library science

Selected publications

• Modern Nonconvex Nondifferentiable Optimization

  Society for Industrial and Applied Mathematics eBooks · 2021 · 57 citations

  Senior authorCorresponding
  DOI

• MultiComposite Nonconvex Optimization for Training Deep Neural Networks

  SIAM Journal on Optimization · 2020 · 28 citations

  Senior authorCorresponding

  We present in this paper a novel deterministic algorithmic framework that enables the computation of a directional stationary solution of the empirical deep neural network training problem formulated as a multicomposite optimization problem with coupled nonconvexity and nondifferentiability. This is the first time to our knowledge that such a sharp kind of stationary solution is provably computable for a nonsmooth deep neural network. Allowing for arbitrary finite numbers of input samples and tr…

  DOI

• Two-Stage Stochastic Programming with Linearly Bi-parameterized Quadratic Recourse

  SIAM Journal on Optimization · 2020 · 16 citations

  Related DatabasesWeb of Science You must be logged in with an active subscription to view this.Article DataHistorySubmitted: 23 July 2019Accepted: 15 June 2020Published online: 21 September 2020Keywordstwo-stage stochastic programming, difference-of-convex, directional stationarityAMS Subject Headings90C15, 90C26Publication DataISSN (print): 1052-6234ISSN (online): 1095-7189Publisher: Society for Industrial and Applied MathematicsCODEN: sjope8

  PublisherDOI

• Comparing solution paths of sparse quadratic minimization with a Stieltjes matrix

  Mathematical Programming · 2023-05-04 · 6 citations

  articleOpen accessSenior author

  Abstract This paper studies several solution paths of sparse quadratic minimization problems as a function of the weighing parameter of the bi-objective of estimation loss versus solution sparsity. Three such paths are considered: the “ $$\ell _0$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mi>ℓ</mml:mi><mml:mn>0</mml:mn></mml:msub></mml:math> -path” where the discontinuous $$\ell _0$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mi>ℓ</mml:…

  PublisherOA PDFDOI

• Analysis of a Class of Minimization Problems Lacking Lower Semicontinuity

  Mathematics of Operations Research · 2024-08-27 · 5 citations

  articleSenior author

  The minimization of nonlower semicontinuous functions is a difficult topic that has been minimally studied. Among such functions is a Heaviside composite function that is the composition of a Heaviside function with a possibly nonsmooth multivariate function. Unifying a statistical estimation problem with hierarchical selection of variables and a sample average approximation of composite chance constrained stochastic programs, a Heaviside composite optimization problem is one whose objective and…

  PublisherDOI

Recent grants

• Analysis and Control of Complementary Systems

  NSF · $225k · 2005–2007

• Extended Nash Equilibria and Their Applications

  NSF · $148k · 2007–2010

• Analysis and Control of Complementary Systems

  NSF · $114k · 2007–2009

Frequent coauthors

• Gesualdo Scutari

  32 shared

• Francisco Facchinei

  27 shared

• Ying Cui

  University of California, Berkeley

  26 shared

• Zhi‐Quan Luo

  22 shared

• John E. Mitchell

  21 shared

• Daniel P. Palomar

  University of Hong Kong

  13 shared

• Meisam Razaviyayn

  12 shared

• M. Kanat Camlibel

  11 shared

Education

• Ph.D., Operations Research

  University of California, Los Angeles

  1980

• M.S., Operations Research

  University of California, Los Angeles

  1976

• B.S., Mathematics

  National Taiwan University

  1974

Awards & honors

• Elected a member of the National Academy of Engineering in F…
• Distinguished Professor at USC (April 2023)
• Fellow of the Institute for Operations Research and Manageme…
• John von Neumann Theory Prize (2019)
• George B. Dantzig Prize (2003)

Similar researchers at University of Southern California

• Carl F Kesselmanh-80
• Maged M. Dessoukyh-51
• Sheldon Mark Rossh-51