I'm a fifth-year CS Ph.D. student at UC Berkeley working with Yun S. Song. I am broadly interested in developing methods in statistical machine learning, probabilistic modeling, and high-dimensional statistics as well as its real-world applications, in particular, I have worked on genomics, healthcare, and demand forecasting in the past. In addition, I have had the good fortune of interning with Lawrence Murrayg at Uber AI Labs where I worked on Bayesian online learning methods for time series. Prior to Berkeley, I received an M.Eng in Computer Science from MIT and a B.S. in Mathematics and Computer Science from MIT. I was funded by the NSF Graduate Research Fellowship.
Email: chanjed AT berkeley DOT edu
- Online Sequential Monte Carlo for Nonstationary Time-Series Using Stochastic Networks. In Submission.
- Exchangeable Variational Autoencoders for Genomics. *Equal contribution. In Submission.
- A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks. NeurIPS 2018 (Spotlight Talk). [arXiv][Software]
- Early human dispersals within the Americas. *Equal contribution. Science. [Journal] [Press]
- Two-Locus Likelihoods Under Variable Population Size and Fine-Scale Recombination Rate Estimation. *Equal contribution. Genetics. [Journal][Software]
- Determination and Validation of Thresholds of Anterior Chamber Parameters by Dedicated Anterior Segment Optical Coherence Tomography. American Journal of Opthalmology. [Journal]
- Exchangeable Variational Autoencoders for Genomics. Advances in Approximate Bayesian Inference (AABI) 2019 (Poster).
- Exchangeable Variational Autoencoders for Genomics. Probabilistic Modeling in Genomics 2019 (Talk).
- A Structured Permutation-Equivariant Network for Reference-free Archaic Admixture. NIPS Machine Learning for Comp Bio 2017 (Talk). Best Talk Award.
- A Stitched HMM Algorithm for Improved rjMCMC Estimation for Fine-Scale Recombination Rate Estimation. Probabilistic Modeling in Genomics 2016 (Poster).