Mario Díaz

activity

20182020

most citedOn the Noise-Information Separation of a Private Principal Component Analysis Scheme

1 citations · 3 across the 4 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2023

Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses

Shahab Asoodeh, Mario Diaz

The Noisy-SGD algorithm is widely used for privately training machine learning models. Traditional privacy analyses of this algorithm assume that the internal state is publicly rev…

cs.LG2019

A Tunable Loss Function for Binary Classification

Tyler Sypherd, Mario Diaz, Lalitha Sankar +1

We present $α$ -loss, $α \in [1, \infty]$ , a tunable loss function for binary classification that bridges log-loss ( $α = 1$ ) and $0$ - $1$ loss ( $α = \infty$ ). We prove that $α$ -loss has a…