activity
20152021
most citedStochastic Neighbor Embedding separates well-separated clusters

15 citations · 15 across the 4 of their papers we have counts for

collaborators

7 papers

stat.ML2021

Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features

Uri Shaham, Ofir Lindenbaum, Jonathan Svirsky +1

Modern datasets often contain large subsets of correlated features and nuisance features, which are not or loosely related to the main underlying structures of the data. Nuisance f…

cs.LG2020

Differentiable Unsupervised Feature Selection based on a Gated Laplacian

Ofir Lindenbaum, Uri Shaham, Jonathan Svirsky +2

Scientific observations may consist of a large number of variables (features). Identifying a subset of meaningful features is often ignored in unsupervised learning, despite its po…

cs.LG2020

Learning to Ask Medical Questions using Reinforcement Learning

Uri Shaham, Tom Zahavy, Cesar Caraballo +3

We propose a novel reinforcement learning-based approach for adaptive and iterative feature selection. Given a masked vector of input features, a reinforcement learning agent itera…

cs.CV2018

Automated Characterization of Stenosis in Invasive Coronary Angiography Images with Convolutional Neural Networks

Benjamin Au, Uri Shaham, Sanket Dhruva +7

The determination of a coronary stenosis and its severity in current clinical workflow is typically accomplished manually via physician visual assessment (PVA) during invasive coro…

stat.ML2018

Defending against Adversarial Images using Basis Functions Transformations

Uri Shaham, James Garritano, Yutaro Yamada +5

We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Speci…

stat.ML201715 cited

Stochastic Neighbor Embedding separates well-separated clusters

Uri Shaham, Stefan Steinerberger

Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques -- despite their popularity, no theoretical results are known. We prove that the…