15 citations · 52 across the 14 of their papers we have counts for
5 papers · 1 filter
Interval-based Prediction Uncertainty Bound Computation in Learning with Missing Values
Hiroyuki Hanada, Toshiyuki Takada, Jun Sakuma +1
The problem of machine learning with missing values is common in many areas. A simple approach is to first construct a dataset without missing values simply by discarding instances…
Differentially Private Empirical Risk Minimization with Input Perturbation
Kazuto Fukuchi, Quang Khai Tran, Jun Sakuma
We propose a novel framework for the differentially private ERM, input perturbation. Existing differentially private ERM implicitly assumed that the data contributors submit their…
Efficiently Bounding Optimal Solutions after Small Data Modification in Large-Scale Empirical Risk Minimization
Hiroyuki Hanada, Atsushi Shibagaki, Jun Sakuma +1
We study large-scale classification problems in changing environments where a small part of the dataset is modified, and the effect of the data modification must be quickly incorpo…
Secure Approximation Guarantee for Cryptographically Private Empirical Risk Minimization
Toshiyuki Takada, Hiroyuki Hanada, Yoshiji Yamada +2
Privacy concern has been increasingly important in many machine learning (ML) problems. We study empirical risk minimization (ERM) problems under secure multi-party computation (MP…
Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences
Kazuto Fukuchi, Jun Sakuma
Fairness-aware learning is a novel framework for classification tasks. Like regular empirical risk minimization (ERM), it aims to learn a classifier with a low error rate, and at t…