• Publicationsclose
• Other research productsclose
• 2017-2021close
• Open Access close
• QA close
• BG close
• arXiv.org e-Print Archive close

We introduce leave-one-out unfairness, which characterizes how likely a model's prediction for an individual will change due to the inclusion or removal of a single other person in the model's training data. Leave-one-out unfairness appeals to the idea that fair decisio...

Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing interest in low-resource machine tran...

A protocol by Ishai et al.\ (FOCS 2006) showing how to implement distributed $n$-party summation from secure shuffling has regained relevance in the context of the recently proposed \emph{shuffle model} of differential privacy, as it allows to attain the accuracy levels...

We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. W...

Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational c...

We study the low rank approximation problem of any given matrix $A$ over $\mathbb{R}^{n\times m}$ and $\mathbb{C}^{n\times m}$ in entry-wise $\ell_p$ loss, that is, finding a rank-$k$ matrix $X$ such that $\|A-X\|_p$ is minimized. Unlike the traditional $\ell_2$ setting...

The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community. Unsupervised strategies to learning are particularly appealing as they can utilize much larger and varied monocular video datasets durin...

We examine the effects of an impending cluster merger on galaxies in the large scale structure (LSS) RX J0910 at $z =1.105$. Using multi-wavelength data, including 102 spectral members drawn from the Observations of Redshift Evolution in Large Scale Environments (ORELSE...

We report the results of optical spectroscopy of the Small Magellanic Cloud supernova remnant (SNR) MCSNR J0127-7332 and the mass donor Be star, 2dFS 3831, in its associated high-mass X-ray binary SXP 1062 carried out with the Southern African Large Telescope (SALT). Us...

Based on the Bethe-Salpeter equation eigenstates, we present a first-principles many-body formalism for calculating the two-photon absorption (TPA) coefficient of semiconductors. We apply this formalism to calculate the TPA spectra of MoS2 and WS2 monolayers. The all-el...