6 citations · 9 across the 2 of their papers we have counts for
6 papers
CPR: Classifier-Projection Regularization for Continual Learning
Sungmin Cha, Hsiang Hsu, Taebaek Hwang +2
We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired b…
Obfuscation via Information Density Estimation
Hsiang Hsu, Shahab Asoodeh, Flavio du Pin Calmon
Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework…
Correspondence Analysis Using Neural Networks
Hsiang Hsu, Salman Salamatian, Flavio P. Calmon
Correspondence analysis (CA) is a multivariate statistical tool used to visualize and interpret data dependencies. CA has found applications in fields ranging from epidemiology to…
Correspondence Analysis of Government Expenditure Patterns
Hsiang Hsu, Flavio P. Calmon, José Cândido Silveira Santos Filho +2
We analyze expenditure patterns of discretionary funds by Brazilian congress members. This analysis is based on a large dataset containing over million expenses made publicly a…
Generalizing Correspondence Analysis for Applications in Machine Learning
Hsiang Hsu, Salman Salamatian, Flavio P. Calmon
Correspondence analysis (CA) is a multivariate statistical tool used to visualize and interpret data dependencies by finding maximally correlated embeddings of pairs of random vari…
Generalizing Bottleneck Problems
Hsiang Hsu, Shahab Asoodeh, Salman Salamatian +1
Given a pair of random variables and two convex functions and , we introduce two bottleneck functionals as the lower and upper boundaries of the two-d…