We propose Path Disruption Games (PDGs), which consider collaboration between agents attempting stop an adversary from travelling from a source node to a target node in a graph. P...
Generating a random sampling of program trees with specified function and terminal sets is the initial step of many program evolution systems. I present a theoretical and experim...
In this note we consider a simple reformulation of the traditional power iteration algorithm for computing the stationary distribution of a Markov chain. Rather than communicate t...
A novel solution to the reliable multicast problem is the “digital fountain” approach, in which data is encoded with an erasure protection code before transmission, and receiv...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...