We now prove Lemma 3.1, showing that Algorithm 3 can be used to reduce the overall graph degree. There are two parts to doing this. First, we need to amplify the success probability of Lemma 3.2, which only showed a degree reduction in expectation, …

We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function arou…

Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language processing community. In this paper, we propose a generative, unsupervised ranking model for entity …

We propose a framework for learning beam search policies using imitation learning. We provide regret guarantees for both new and existing algorithms for learning beam search policies. One of the main contributions is formulating learning beam search…

We briefly discuss our findings, offer some guiding principles for evaluating new benchmarks and algorithms, and speculate on why some of these problems may have gone under the radar. Our goal is not to blame the creators of past datasets but instea…

We have shown that for bounded deletion streams, many important L0 and L1 streaming problems can be solved more efficiently. For L1, the fact the fi’s are approximately preserved under sampling poly(α) updates paves the way for our results, whereas …

Padovani describes a calculus similar to ours [19] where he interprets internal and external choices as union and intersection, respectively. This resembles what we did in section 3.4 except we keep singleton choices at the type and term levels to m…

In this paper we present a direct analysis for hitting time of SGLD for the first and second order stationary points. Our proof only relies on basic linear algebra, and probability theory. Through this directly analysis, we show how different factor…

In this note we have established tight minimax rates for the problem of homology inference in the noiseless case. The intuition behind the construction extends to the noisy cases considered in [1] in a straightforward way.

We thank John Gilbert and Gramoz Goranci for many helpful discussions regarding various topics in this paper. We also would like to acknowledge Animesh Fatehpuria for independently obtaining the construction of covering set systems in Lemma 8.3.