2 papers
stat.ML2015
Belief Flows of Robust Online Learning
Pedro A. Ortega, Koby Crammer, Daniel D. Lee
This paper introduces a new probabilistic model for online learning which dynamically incorporates information from stochastic gradients of an arbitrary loss function. Similar to p…
cs.AI2011
Information, Utility & Bounded Rationality
Pedro A. Ortega, Daniel A. Braun
Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we employ an axiomatic framewo…