• I am a sixth-year Ph.D. candidate in Computer Science Department at Harvard University, working with Professor Flavio P. Calmon.
• My research interests on Responsible AI lie in promoting the interpretability of representations, improving privacy and fairness, and understanding prediction uncertainty in machine learning. Recently, I am also working on predictive multiplicity, the similarity of neural representations, and physics-informed learning.
• I received M.S. in Electrical Engineering in 2016, and B.S. in Mathematics and Electrical Engineering in 2014, both from National Taiwan University (NTU). Previously, I worked with Professor Kwang-Cheng Chen on crowdsourcing and wireless caching, and with Professor Huan-Cheng Chang on fluorescent nano-diamonds and micro-imaging.

News

Oct, 2022: I received the NeurIPS Scholar Award.

Oct, 2022: Our paper Beyond Adult and COMPAS: Fairness in Multi-Class Prediction via Information Projection is selected as Oral Presentation in NeurIPS 2022.

Sept, 2022: Our paper Rashomon Capacity: A Metric for Predictive Multiplicity in Classification is accepted by NeurIPS 2022. [Poster][Slides]

Aug, 2022: I am selected as Meta Research PhD Fellowship Spotlight. [Link]

July, 2022: Our works Rashomon Capacity: A Metric for Predictive Multiplicity in Probabilistic Classification and Beyond Adult and COMPAS: Fairness in Multi-Class Prediction are presented in ICML 2022, RDMDE and DFUQ workshops.

Jan, 2022: Check out our latest work on Robust Hybrid Learning With Expert Augmentation. [Paper]

Nov, 2021: Our paper Generalizing Correspondence Analysis for Applications in Machine Learning is accepted by IEEE TPAMI. [Paper]

Jun, 2021: Our paper A Survey on Privacy from Statistical, Information and Estimation-Theoretic Views is accepted by IEEE BITS the Information Theory Magazine. [Paper]

Mar, 2021: I am awarded with Facebook PhD Fellowship

Dec, 2020: Our paper CPR: Classifier-projection regularization for continual learning is accepted by ICLR 2021. [Paper]

Dec, 2020: Our paper Obfuscation via information density estimation is accepted by AISTATS 2020. [Paper]

Nov, 2019: Our paper Discovering Information-Leaking Samples and Features is selected as spotlight talk in NeurIPS PriML 2019. [Paper][Slides][Poster]

Apr, 2019: Our paper Information-Theoretic Privacy Watchdogs is accepted by ISIT 2019. [Paper][Slides]

Dec, 2018: Our paper Correspondence Analysis Using Neural Networks is accepted by AISTATS 2019. [Paper][Poster]

Dec, 2018: Our paper Correspondence Analysis of Government Expenditure Patterns will be presented in 2019 NeurIPS Workshops. [Paper][Poster]

Jun, 2018: Check out our latest work on Deep Orthogonal Representations: Fundamental Properties and Applications. [Paper]

May, 2018: I am invited to New England Machine Learning (NEML) Day at Microsoft Research. [Poster]

Apr, 2018: Our paper Generalizing Bottleneck Problems is accepted by ISIT 2018. [Paper][Slides]

Contact

Email: hsianghsu(at)g(dot)harvard(dot)edu
Office: Science and Engineering Complex, 150 Western Avenue., Room 3.413, Boston, MA 02134