John von Neumann Theory Prize
Share:
2018 Awardee(s)
- Dimitri P. Bertsekas,
Massachusetts Institute of Technology
- John N. Tsitsiklis, Massachusetts Institute of Technology
The 2018 INFORMS John von Neumann theory prize is awarded to Dimitri P. Bertsekas and John N. Tsitsiklis for contributions to Parallel and Distributed Computation as well as Neurodynamic Programming. Working together and independently, Bertsekas and Tsitsiklis have made seminal contributions to both these fields. They unified ideas and built solid theoretical foundations while these fields were still relatively nascent, thus greatly enhancing subsequent development of rigorous theory.
Their monograph Parallel and Distributed Computation: Numerical Methods represents a significant achievement in the field. The work builds on and extends the authors’ extensive previous work in this area, identifying the tolerance of algorithms to asynchronous implementations and a number of positive convergence results. An antecedent work of particular significance to the operations research community is the paper by Tsitsiklis, Bertsekas and Athans which provides seminal analysis of asynchronous implementations of deterministic and stochastic gradient algorithms. This line of inquiry has recently found application in the analysis of descent algorithms for neural network training and other machine learning problems. Their work in distributed computation has also had significant impact on the areas of distributed network control and distributed detection.
Their monograph Neuro-Dynamic Programming helped provide a unified theoretical treatment of the wide variety of reinforcement learning algorithms by building connections to the dynamic programming and distributed computation literature. This has proven extremely valuable in bringing theoretical rigor to a field of rapid, empirical innovation. The authors’ contributions in this area go beyond providing a theoretical foundation that other could build on. The authors have made significant original contributions to value function learning, temporal difference methods and actor-critic algorithms.
The work of Bertsekas and Tsitsiklis is characterized by its innovation, depth and clarity, and it has had tremendous impact as evident from the large number of citations. Their two joint monographs are among their individual five most cited works, making the award of a joint prize particularly appropriate. Bertsekas and Tsitsiklis have brought the fields of computer science and operations research closer together through unifying theory.
Purpose of the Award
2018 Committee Chair
Sunil Kumar
Johns Hopkins University
Baltimore, MD 21218
U.S.A.
email: lonathomas@jhu.edu
The John von Neumann Theory Prize is awarded annually to a scholar (or scholars in the case of joint work) who has made fundamental, sustained contributions to theory in operations research and the management sciences. The award is given each year at the INFORMS Annual Meeting if there is a suitable recipient. Although the Prize is normally given to a single individual, in the case of accumulated joint work, the recipients can be multiple individuals.
The Prize is awarded for a body of work, typically published over a period of several years. Although recent work should not be excluded, the Prize typically reflects contributions that have stood the test of time. The criteria for the Prize are broad, and include significance, innovation, depth, and scientific excellence.
The award is $5,000, a medallion and a citation.
Nominations due August 1, 2018
The Prize Committee is currently seeking nominations, which should be in the form of a letter (preferably email) addressed to the prize committee chair (below), highlighting the nominee's accomplishments. Although the letter need not contain a detailed account of the nominee's research, it should document the overall nature of his or her contributions and their impact on the profession, with particular emphasis on the prize's criteria. The nominee's curriculum vitae, while not mandatory, would be helpful.
About the Award/Namesake
John von Neumann was a brilliant mathematician, synthesizer, and promoter of the stored program concept, whose logical design of the IAS became the prototype of most of its successors - the von Neumann Architecture. von Neumann was invited to visit Princeton University in 1930, and when the Institute for Advanced Studies was founded there in 1933, he was appointed to be one of the original six Professors of Mathematics, a position which he retained for the remainder of his life. Postwar von Neumann concentrated on the development of the Institute for Advanced Studies (IAS) computer and its copies around the world. His work with the Los Alamos group continued and he continued to develop the synergism between computers capabilities and the needs for computational solutions to nuclear problems related to the hydrogen bomb.
Past Awardees
John N. Tsitsiklis, Massachusetts Institute of Technology
The Institute for Operations Research and the Management Sciences
5521 Research Park Drive, Suite 200Catonsville, MD 21228 USA
phone 1 443-757-3500
phone 2 800-4INFORMS (800-446-3676)
fax 443-757-3515
email informs@informs.org