Theoretically, we prove that SFB can learn an asymptotically-optimal predictor without test-domain labels. Empirically, we demonstrate the effectiveness of SFB on real and synthetic data.

Recently, there has been significant interest in utilizing this information in the context of deep neural networks; however,relatively little isknown about the quality ofexisting approximationsinthiscontext.

Recently, there has been significant interest in utilizing this information in the context of deep neural networks; however,relatively little isknown about the quality ofexisting approximationsinthiscontext.

Ensemble sampling serves as apractical approximation to Thompson sampling when maintaining anexact posterior distribution overmodel parameters iscomputationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling isapplied tothe linear bandit problem.

Toeffectively tackle this issue and learn more expressiveprior models, wedevelop theadaptivemulti-stage density ratio estimation which breaks the estimation into multiple stages and learn different stages ofdensity ratiosequentially andadaptively. Thelatent priormodel canbe gradually learned using ratio estimated in previous stage so that the final latent spaceEBMpriorcanbenaturally formed byproduct ofratiosindifferentstages. The proposed method enables informativeand much sharper prior than existing baselines, and can be trained efficiently.