activity
19992005
most citedDistributed Control by Lagrangian Steepest Descent

7 citations · 18 across the 5 of their papers we have counts for

collaborators

10 papers

cond-mat.other20051 cited

An adaptive Metropolis-Hastings scheme: sampling and optimization

David H. Wolpert, Chiu Fan Lee

We propose an adaptive Metropolis-Hastings algorithm in which sampled data are used to update the proposal distribution. We use the samples found by the algorithm at a particular s…

cs.MA20047 cited

Distributed Control by Lagrangian Steepest Descent

David H. Wolpert, Stefan Bieniawski

Often adaptive, distributed control can be viewed as an iterated game between independent players. The coupling between the players' mixed strategies, arising as the system evolves…

cond-mat.stat-mech20045 cited

Information Theory - The Bridge Connecting Bounded Rational Game Theory and Statistical Physics

David H. Wolpert

A long-running difficulty with conventional game theory has been how to modify it to accommodate the bounded rationality of all real-world players. A recurring issue in statistical…

cond-mat.stat-mech20035 cited

Product Distribution Field Theory

David H. Wolpert

This paper presents a novel way to approximate a distribution governing a system of coupled particles with a product of independent distributions. The approach is an extension of m…

cond-mat.dis-nn2003

Collectives for the Optimal Combination of Imperfect Objects

Kagan Tumer, David Wolpert

In this letter we summarize some recent theoretical work on the design of collectives, i.e., of systems containing many agents, each of which can be viewed as trying to maximize an…

cs.DC1999

Avoiding Braess' Paradox through Collective Intelligence

Kagan Tumer, David H. Wolpert

In an Ideal Shortest Path Algorithm (ISPA), at each moment each router in a network sends all of its traffic down the path that will incur the lowest cost to that traffic. In the l…