David H. Wolpert
Santa Fe Institute & CSH External Faculty
David Wolpert is a professor at the Santa Fe Institute and adjunct professor at Arizona State University. His degrees in physics are from Princeton and the University of California.
Before his current position he was the Ulam scholar at the Center for Nonlinear Studies, and before that at NASA Ames Research Center and a consulting professor at Stanford University, where he formed the Collective Intelligence group. He has worked at IBM and a data mining start-up, and is external faculty at numerous international institutions.
David has over 21,000 citations. Most of his papers are in thermodynamics of computation, foundations of physics, dynamics of social organizations, machine learning, game theory, distributed optimization, and molecular biology. In particular his machine learning technique of stacking was instrumental in both winning entries for the Netflix competition. His papers on the no free lunch theorems have over 7,000 citations.
Most of his current research involves two topics: combining recent breakthroughs in nonequilibrium statistical physics with computer science theory to lay the foundations of a complete theory of the thermodynamics of computation; and modelling social organization (command and communication networks within social groups) using information theory.
David is the author of three books (and co-editor of several more), and over 200 papers. He has three patents. David is an associate editor at over half a dozen journals, has received numerous awards, and is a fellow of the IEEE.
A. Kolchinsky, et al.
Dependence of integrated, instantaneous, and fluctuating entropy production on the initial state in quantum and classical processes
Physical Review E 104 (2021) 054107
D. Wolpert, D. Kinney
Noisy Deductive Reasoning: How Humans Construct Math, and How Math Constructs Universes
in: A. Aguirre et al. (eds), Undecidability, Uncomputability and Unpredictability, Springer Cham 2021, 147-167
Uncertainty relations and fluctuation theorems for Bayes nets
Physical Review Letters 125 (2020) 200602