Empirical results show that our approach can achieve substantial improvement over the state-of-the-art baselines.

We study the problem of how to repeatedly sell to a buyer running a no-regret,mean-based algorithm. Previous work [Braverman et al., 2018] shows that it ispossible to design effective mechanisms in such a setting that extract almost allof the economic surplus, but these mechanisms require the buyer's values each

In addition, our algorithm also adapts to scenarios where the repulsion is onlyrequired among nearby fewitems intheresult sequence.

But spectral clustering remains a frequently used baseline, and a serious contender to state-of-the-art graphembeddingmethods,e.g.[20,11,28,22].

Therefore, many existing SLP vectorization schemes are driven by hand-crafted heuristics (Liu et al., 2012;

Neural Information Processing Systems http://nips.cc/

Is Interaction Necessaryfor Distributed Private Learning?

In this paper, we aim to learn alow-dimensional Euclidean representation from aset of constraints of the form "itemj is closer to itemithan itemk".

We consider the problem of learning optimal reserve price in repeated auctions against non-myopic bidders, who may bidstrategically inorder togaininfuture rounds even if the single-round auctions are truthful.

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.