Tim Shi 施天麟
PhD Student, Stanford University
Co-founder, AI+ ClubEmail tianlins [at] cs [dot] stanford [dot] edu
Curriculum Vitae [PDF]
I've done lots of research in Bayesian machine learning during my undergrad. The following are the papers I've written. Now, I am working on a more ambitious project in the intersecion of AI and human-computer interaction. Stay tuned! Part of it has exposed in OpenAI Universe.
Online Bayesian Passive-Aggressive Learning
Tianlin Shi and Jun Zhu.
Journal of Machine Learning Research 2017 (in press)
Improving Survey Aggregation with Sparsely Represented Signals
Tianlin Shi, Forest Agostinelli, Matthew Staib, David Wipf, Thomas Moscibroda
KDD 2016: The 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Max-Margin Deep Generative Models
Chongxuan Li, Jun Zhu, Tianlin Shi and Bo Zhang.
NIPS 2015: The Twenty-ninth Annual Conference on Neural Information Processing Systems (NIPS).
Learning Where to Sample in Structured Prediction
Tianlin Shi, Jacob Steinhardt and Percy Liang
AISTATS 2015: Accepted as Oral (6.1%).
The 18th International Conference on Artificial Intelligence and Statistics, San Diego, California, USA.
Correlated Compressive Sensing for Networked Data
Tianlin Shi, Da Tang, Liwen Xu and Thomas Moscibroda
UAI 2014: 30th Conference on Uncertainty in Artificial Intelligence, Quebec City, Canada, July 2014.
A Reverse Hierarchy Model for Predicting Eye Fixations
Tianlin Shi, Liang Ming and Xiaolin Hu.
CVPR 2014: IEEE Conference on Computer Vision and Pattern Recognition, Columbus, Ohio, USA., 2014
A Fully Polynomial-Time Approximation Scheme for Approximating a Sum of Random Variables
Jian Li*, and Tianlin Shi*.
ORL: Operations Research Letters 42.3 (2014): 197-202.
*Author names follow alphabetic order.
This paper is based on a pset problem from the course Algorithm Design, taught by Prof. Jian Li.
Gradient-based inference for higher-order probabilistic programming languages
Tianlin Shi, Alexey Radul and Vikash Mansinghka
NEML 2014: Workshop at New England Machine Learning Day
Stanford, CA. From 09/2015
San Francisco, CA. Summer 2015
People take tons of of photos to memorize life moments. I worked on better curating those personal photos. Learn more
At Hack Week, I built a camera-upload app for Google Glass. So it takes photos every few seconds and upload to Dropbox. Meanwhile, CV algorithms at backend curate those photos and aggregate into events like meeting people, reading documents, etc.
I presented the project to Drew Houston, CEO of Dropbox.
Beijing, China. Spring 2015
Survey companies spend millions of dollars each year to collect data such as social polls. We developed an aggregation technique to significantly reduce that cost.
MIT, Cambridge, MA. Spring 2014
Spend a couple of months at MIT. Worked on a probabilistic programming system called Venture.
Beijing, China. 2011 - 2015