We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The fi...
Traditional tensor decompositions such as the CANDECOMP / PARAFAC (CP) and Tucker decompositions yield higher-order principal components that have been used to understand tensor d...
Temporal Clustering (TC) refers to the factorization of multiple time series into a set of non-overlapping segments that belong to k temporal clusters. Existing methods based on e...
We present an algorithm for fast posterior inference in penalized high-dimensional state-space models, suitable in the case where a few measurements are taken in each time step. W...
We prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...