I am a postdoctoral researcher in Caltech Computing and Mathematical Sciences. Before that, I received my Ph.D. degree in Computer Science from University of Southern California.
I work on machine learning for large-scale time series and its applications. I am generally interested in sequential decision making, optimization and spatiotemporal modeling. My work has been applied to learning dynamical systems, intelligent transportation, and climate informatics. For more details, see my curriculum vitae and research statement.
In fall 2018, I will be joining Northeastern University as an assistant professor. And I am looking for talented students who are excited about machine learning! Read More
Contact Info
- E-mail: rose [at] caltech [dot] edu.
- Address: 1200 E California Blvd 305-16, Pasadena, CA 91125
News
- Feb 2018: New paper on Multi-resolution Tensor Learning!
- Jan 2018: ICLR 2018 Diffusion Convolutional RNN!
- Dec 2017: AISTATS 2018 Tensor regression meets Gaussian Processes!
- Dec 2017: Won best poster award for Long-term Forecasting using Tensor-Train RNNs at NIPS TSW!
- Nov 2017: New paper on Diffusion Convolutional RNN selected for oral at NIPS TSW!
- Nov 2017: New paper on Long-term Forecasting using Tensor-Train RNNs!
- Oct 2017: Give talks at DOLCIT seminar !
- August 2017: Starting post-doc at Caltech CMS !
- July 2017: Give talks at Peking University, DiDi Chuxing, JiaoTong University and Zhejiang University !
- June 2017: Co-organize time series workshop at ICML 2017, please submit!
- May 2017: New paper on Graph Convolutional Recurrent Neural Network for Spatiotemporal Forecasting!
- April 2017: SDM Best paper runner-up for Deep Learning for Traffic Forecasting!
- April 2017: Won ACM scholarship for Turing Award Celebration!
- March 2017: Giving a talk at Brown University!
- Feb 2017: Giving a talk at Georgia Tech!
- Dec 2016: Co-organizing NIPS workshop on Learning with Tensors: Why Now and How? (Tensor-Learn 2016)!
- Sep 2016: Invited Speaker at AI With The Best!
- August 2016: Visiting Prof. Christopher Ré 's group at Stanford!
- May 2016: Papers accepted in ICML and KDD 2016!
- April 2016: Co-organizing Women in Machine Learning Workshop (WiML 2016) in Barcelona, Spain!
Projects
Deep Structured Model for Nonlinear Dynamics
Expressive models for learning nonlinear dynamical system
Long-term forecasting in environments with nonlinear dynamics is highly challenging, since there exist long-term temporal dependencies, higher-order correlations and sensitivity to error propagation. We present a novel family of neural sequence models, that learn the nonlinear dynamics directly using higher order moments and high-order state transition functions.
Tensor Learning for Spatiotemporal Analysis
A scalable framework for analyzing spatiotemporal data
Large-scale spatiotemporal data such as climate measurements, location-based social networks have complex structures. In this project, we develop a scalable framework based on low-rank tensor learning to analyze them. We propose a series of algorithms ranging from offline, online to memory efficient learning to solve the problem. We show that our framework can produce accurate predictions in a scalable way and discover interesting patterns in spatiotemporal data.
Spatiotemporal Models for Traffic Prediction
A spatiotemporal approach to predict road network traffic
Given a series of road network snapshots, we propose a latent space model to capture its topological and temporal properties. We present an incremental online algorithm which sequentially and adaptively learns the spatiotemporal patterns. Our framework enables real-time traffic prediction on a large volumne of Los Angeles traffic sensor data.
Publications
Preprints
Conferences