Two reasons why I think that A Beautiful Algorithm? The Risks of Automating Online Transactions is way off in its report on an otherwise interesting paper [Econometrics for Learning Agents]. Continue reading
Kuhn enrolled at Princeton in the fall of 1947. He wrote his doctoral dissertation in group theory under the direction of Ralph Fox. Concurrently, he joined mathematics professor A.W. Tucker and fellow graduate student David Gale in a hastily organized summer project to study the suspected equivalence between linear programming and matrix game theory. That project, he later wrote, “set the course of my subsequent academic career, which has centered around the applications of mathematics to economics.” In 1980, the three shared the John von Neumann Theory Prize of the Operations Research Society of America (now part of INFORMS) for their pioneering work in game theory and optimization.
 Bandits with concave rewards and convex knapsacks, Shipra Agrawal and Nikhil R. Devanur
Introduces and gives polynomial-time near-optimal algorithms for a general model for bandit exploration-exploitation. The algorithm is an extension of the Upper Confidence Bound (UCB) algorithm for the multi-armed bandits problem. The new framework allows them to give more efficient algorithms for other problems such as Blackwell approachability, online convex optimization and conditional-gradient/projection-free/Frank-Wolfe algorithm.