Word Sense Disambiguation (WSD)4 [36] is a dataset to identify the most appropriate sense (out of three given senses) of the word "president" in a given paragraph.

When training complex neural networks, memory usage can be an important bottleneck.

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.

Asynchronous Gibbs sampling has been recently shown to be fast-mixing and an accurate method for estimating probabilities of events on a small number of variables of a graphical model satisfying Dobrushin's condition [DSOR16].

Wegivethe first efficient algorithms proven to succeed in the correlated Erdös-Rényi model (Pedarsani and Grossglauser, 2011). Specifically, we give apolynomial time algorithm for thegraphsimilarity/hypothesis testingtaskwhich worksforeveryconstant level of correlation between the two graphs that can be arbitrarily close to zero. We also give a quasi-polynomial (nO(logn) time) algorithm for thegraph matching task of recovering the permutation minimizing the symmetric difference in this model.

We show that if the predictor is accurate, we can efficiently bypass these impossibility results and achieve a constant-factor approximation to the optimal solution, i.e., consistency.

Let k be the collection of distributions over the alphabet[k]:= {1,2,...,k}, and [k] be the set of finite sequences over[k].

Many high-dimensional statistical inference problems are believed to possess inherent computational hardness. Various frameworks have been proposed to give rigorous evidence for such hardness, including lower bounds against restricted models of computation (such as low-degree functions), as well as methods rooted in statistical physics that are based on free energy landscapes. This paper aims to make a rigorousconnectionbetween the seeminglydifferent low-degreeand free-energybased approaches. We define a free-energybasedcriterionfor hardnessand formallyconnectit to the well-establishednotionof low-degree hardness for a broad class of statistical problems, namely all Gaussian additive models and certain models with a sparse planted signal.

Theglobalmodel of differential privacy,which assumes that users trust the data collector, provides strong privacy guarantees and introduces small errors in the output.