A well-known result by Stein shows that regularized estimators with small bias often yield better estimates than unbiased estimators. In this paper, we adapt this spirit to model selection, and propose regularizing unbiased generalization error estimators for stabilization. We trade a small bias in a model selection criterion against a larger variance reduction which has the beneficial effect o...

Applying domain decomposition to the lattice Dirac operator and the associated quark propagator, we arrive at expressions which, with the proper insertion of random sources therein, can provide improvement to the estimation of the propagator. Schemes are presented for both open and closed (or loop) propagators. In the end, our technique for improving open contributions is similar to the “maxima...

We present an algorithm for structured prediction under online bandit feedback. The learner repeatedly predicts a sequence of actions, generating a structured output. It then observes feedback for that output and no others. We consider two cases: a pure bandit setting in which it only observes a loss, and more fine-grained feedback in which it observes a loss for every action. We find that the ...

We consider a quadcopter operating in turbulent windy environment. The environment may be imposed on by structures, landscapes, terrains and most importantly the unique physical phenomena lower atmosphere. Turbulence can negatively impact quadcopter's performance operations. Modeling turbulence as stochastic random input, we investigate control designs that reduce effects motion. In particular,...