We are interested in a framework of online learning with kernels for lowdimensional, but large-scale and potentially adversarial datasets. We study the computational and theoretical performance of online variations of kernel Ridge regression.

We further show that optimistic posterior sampling can control this Hellinger distance, when we measure model error via data likelihood. This technique allows us to design and analyze unified posterior sampling algorithms with state-of-the-art sample complexity guarantees for many model-based RL settings.

We study pure exploration in bandits, where the dimension of the feature representation can be much larger than the number of arms.

Finally, we extend LESS embeddings to include uniformly sparsified random sign matrices which canbeimplemented efficiently andwhich perform wellinnumericalexperiments.

Finally, we extend LESS embeddings to include uniformly sparsified random sign matrices which canbeimplemented efficiently andwhich perform wellinnumericalexperiments.