Nathan Srebro

activity

20102022

most citedEquality of Opportunity in Supervised Learning

1.9k citations · 2.3k across the 15 of their papers we have counts for

collaborators

Showing stat.MLShow all

3 papers · 1 filter

stat.ML2021★ 1 cited

Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regression

Lijia Zhou, Frederic Koehler, Danica J. Sutherland +1

We study a localized notion of uniform convergence known as an "optimistic rate" (Panchenko 2002; Srebro et al. 2010) for linear regression with Gaussian data. Our refined analysis…

stat.ML2014★ 59 cited

On Symmetric and Asymmetric LSHs for Inner Product Search

Behnam Neyshabur, Nathan Srebro

We consider the problem of designing locality sensitive hashes (LSH) for inner product similarity, and of the power of asymmetric hashes in this context. Shrivastava and Li argue t…

stat.ML2012

Sparse Prediction with the $k$ -Support Norm

Andreas Argyriou, Rina Foygel, Nathan Srebro

We derive a novel norm that corresponds to the tightest convex relaxation of sparsity combined with an $ℓ_{2}$ penalty. We show that this new {\em $k$ -support norm} provides a tig…

Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regression

On Symmetric and Asymmetric LSHs for Inner Product Search

Sparse Prediction with the k-Support Norm

Sparse Prediction with the $k$ -Support Norm