External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...
This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize th...
Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of B...
We study online learnability of a wide class of problems, extending the results of [26] to general notions of performance measure well beyond external regret. Our framework simult...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
We compare the complexity of "internal" and "external" equivalence checking. The former is meant for proving the correctness of a synthesis transformation by w...