I am a fifth year Ph.D. student in Computer Science at Stanford University advised by Stefano Ermon, where I'm affiliated with the SAIL and StatML groups. My research interests lie in probabilistic machine learning methods: in particular, I am interested in developing techniques for better adaptation and controllable generation in generative models, robust representation learning, and various applications.

My research is supported by the NSF GRFP, Stanford Graduate Fellowship, the Qualcomm Innovation Fellowship, and the Two Sigma Diversity PhD Fellowship. I completed my undergraduate studies in CS-Stats at Columbia, where I worked on problems in computational biology as part of the Pe'er lab.

I previously interned at Google Brain in 2019 as part of the Magenta project. In my free time I'm an avid tennis player, runner, and food enthusiast!

Preprints

Neural Network Compression for Noisy Storage Devices.

Berivan Isik, Kristy Choi, Xin Zheng, Tsachy Weissman, Stefano Ermon, H.-S. Philip Wong, Armin Alaghi

arXiv preprint, 2021.

[arXiv][code soon]

Publications

Density Ratio Estimation via Infinitesimal Classification.

Kristy Choi*, Chenlin Meng*, Yang Song, Stefano Ermon

International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

Oral presentation [Top 2.6%]

[arXiv][code soon]

Featurized Density Ratio Estimation.

Kristy Choi*, Madeline Liao*, Stefano Ermon

Uncertainty in Artificial Intelligence (UAI), 2021.

[arXiv][code]

Robust Representation Learning via Perceptual Similarity Metrics.

Saeid Taghanaki*, Kristy Choi*, Amir Khasahmadi, Anirudh Goyal

International Conference of Machine Learning (ICML), 2021.

[arXiv][code soon]

Encoding Musical Style with Transformer Autoencoders.

Kristy Choi, Curtis Hawthorne, Ian Simon, Monica Dinculescu, Jesse Engel

International Conference of Machine Learning (ICML), 2020.

[arXiv] [code]

Fair Generative Modeling via Weak Supervision.

Kristy Choi*, Aditya Grover*, Trisha Singh, Rui Shu, Stefano Ermon

International Conference of Machine Learning (ICML), 2020.

[arXiv] [code] [press]

Meta-Amortized Variational Inference and Learning.

Mike Wu*, Kristy Choi*, Noah Goodman, Stefano Ermon

AAAI Conference on Artificial Intelligence (AAAI), 2020.

[arXiv]

Neural Joint-Source Channel Coding.

Kristy Choi, Kedar Tatwawadi, Aditya Grover, Tsachy Weissman, Stefano Ermon.

International Conference of Machine Learning (ICML), 2019.

Oral Presentation

[pdf] [code]

Single-cell map of diverse immune phenotypes in the breast tumor microenvironment.

Elham Azizi, Ambrose Carr, George Plitas, Andrew Cornish, Catherine Konopacki, Sandhya Prabhakaran, Juozas Nainys, Kenmin Wu, Vaidotas Kiseliovas,
Manu Setty, Kristy Choi, Rachel Fromme, Phuong Dao, Peter McKenney, Ruby Wasti, Krishna Kadaveru, Linas Mazutis, Alexander Rudensky, Dana Pe'er.

Cell, 174(5), 1293-1308, 2018.

[pdf]

Wishbone identifies bifurcating developmental trajectories from single-cell data.

Manu Setty, Michelle Tadmor, Shlomit Reich-Zeliger, Omer Angel, Tomer Salame, Pooja Kathail, Kristy Choi, Sean Bendall, Nir Friedman, Dana Pe'er.

Nature Biotechnology, 34(6), 637-645, 2016.

[pdf]

Workshop Papers

Tensor Decomposition for Single-cell RNA-seq Data.

Kristy Choi*, Ambrose J. Carr*, Sandhya Prabhakaran, Dana Pe'er

Practical Bayesian Nonparametrics Workshop, NeurIPS 2016.

[pdf]

Teaching

Fall 2019: Head Teaching Assistant for CS236: Deep Generative Models at Stanford

Fall 2018: Teaching Assistant for CS236: Deep Generative Models at Stanford

Spring 2017: Head Teaching Assistant for COMS4117: Machine Learning at Columbia

Service

Reviewer: ICML 2021, ICLR 2021, NeurIPS 2020, ICML 2020, UAI 2020, ICLR 2020, AAAI 2020, NeurIPS 2019, ICML 2019, ICLR 2019.

Workshop Co-Organizer: Women in Machine Learning @ NeurIPS 2020; Information Theory & Machine Learning (NeurIPS 2019)