Algorithmic stability is a major theme in learning theory, where seminal results have firmly established its close relationship with generalization. Recent research has further highlighted the intricate interplay between stability and additional properties of interest beyond statistical generalization.

It is desirable to restrict the number of components (i.e., encourage sparsity) for

In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.

The random features method, proposed by Rahimi and Recht [2008], maps the data to a finite dimensional feature space as a random approximation to the feature space of RBF kernels. With explicit finite dimensional feature vectors available, the original KSVM is converted to a linear support vector machine (LSVM), that can be trained by faster algorithms (Shalev-Shwartz et al.