With time running out before the May 12 deadline by which President Trump is to decide whether to pull out of the Iran nuclear deal, the leaders of Israel and Iran weighed in on Sunday, with one calling the agreement "fatally flawed" and the other warning of "historic regret" if the United States rips up the deal. Prime Minister Benjamin Netanyahu of Israel repeated his call for the agreement to be "fully fixed or fully nixed," arguing that while it may have delayed the acquisition of Iran's first bomb, it paves the way for the country to build an entire nuclear arsenal soon after the deal expires. In Iran, President Hassan Rouhani, whose negotiating team reached the nuclear accord with six world powers in 2015, said the Trump administration would come to rue any decision to renounce the agreement. "If America leaves the nuclear deal, this will entail historic regret for it," Mr. Rouhani said in a speech broadcast live on state television. He warned in veiled terms that Iran could consider restarting its now largely mothballed nuclear energy program, which is under inspection of the International Atomic Energy Agency.
We consider the thresholding bandit problem, whose goal is to find arms of mean rewards above a given threshold $\theta$, with a fixed budget of $T$ trials. We introduce LSA, a new, simple and anytime algorithm that aims to minimize the aggregate regret (or the expected number of mis-classified arms). We prove that our algorithm is instance-wise asymptotically optimal. We also provide comprehensive empirical results to demonstrate the algorithm's superior performance over existing algorithms under a variety of different scenarios. Papers published at the Neural Information Processing Systems Conference.
We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is possible to achieve finite expected cumulative regret. We also give problem-dependent lower bounds on the cumulative regret showing that at least in special cases the new algorithm is nearly optimal. Papers published at the Neural Information Processing Systems Conference.
Automated decision-making is one of the core objectives of artificial intelligence. Not surprisingly, over the past few years, entire new research fields have emerged to tackle that task. This blog post is concerned with regret minimization, one of the central tools in online learning. Regret minimization models the problem of repeated online decision making: an agent is called to make a sequence of decisions, under unknown (and potentially adversarial) loss functions. Regret minimization is a versatile mathematical abstraction, that has found a plethora of practical applications: portfolio optimization, computation of Nash equilibria, applications to markets and auctions, submodular function optimization, and more.
Tiger Woods has one regret, and it's not the 2009 cheating scandal that led to the end of his marriage to Elin Nordegren. The 40-year-old professional golfer revealed the one thing that he wishes he could've changed, during an hour-long interview with Charlie Rose on Thursday. "The only regret I have in life is not spending another year at Stanford [University]," Woods told Rose. "I wish I would've had one more year." WATCH: 'Cheater' Banner Flies Over Tiger Woods During U.S. Open.