Distributionally Robust Fair Principal Components via Geodesic Descents

no code implementations • ICLR 2022 • Hieu Vu, Toan Tran, Man-Chung Yue, Viet Anh Nguyen

Principal component analysis is a simple yet useful dimensionality reduction technique in modern machine learning pipelines.

Dimensionality Reduction Fairness

Bayesian Metric Learning for Robust Training of Deep Models under Noisy Labels

no code implementations • 1 Jan 2021 • Toan Tran, Hieu Vu, Gustavo Carneiro, Hung Bui

Label noise is a natural event of data collection and annotation and has been shown to have significant impact on the performance of deep learning models regarding accuracy reduction and sample complexity increase.

General Classification Metric Learning +1