We give the first result for agnostically learning Single-Index Models (...
Optimizing proper loss functions is popularly believed to yield predicto...
Multicalibration is a notion of fairness that aims to provide accurate
p...
A recent line of work shows that notions of multigroup fairness imply
su...
We study the fundamental question of how to define and measure the dista...
We present a new perspective on loss minimization and the recent notion ...
Introduced as a notion of algorithmic fairness, multicalibration has pro...
Estimating the Kullback-Leibler (KL) divergence between two distribution...
Loss minimization is a dominant paradigm in machine learning, where a
pr...
The ratio between the probability that two distributions R and P give to...
Data exploration systems that provide differential privacy must manage a...
We consider the problem of detecting anomalies in a large dataset. We pr...
Say that we are given samples from a distribution ψ over an
n-dimensiona...
Hillview is a distributed spreadsheet for browsing very large datasets t...
We present efficient streaming algorithms to compute two commonly used
a...
We present the design and evaluation of Rapid, a distributed membership
...