Abner

My PhD work is in Statistical Machine Learning. I study generalizations to Structured Prediction methods — Probabilistic Graphical Models (PGMs), Markov Random Fields (MRFs), Structured Support Vector Machines (Structured SVMs) — that leverage multiple outputs for increased expressivity and performance. My research emphasizes models and inference/learning algorithms for generating multiple diverse predictions.

I have graduated and am taking a temporary leave from full-time research during fall 2014 to work on a VC funded startup.

During my PhD, I was advised by Rob Rutenbar and I collaborated closely with Dhruv Batra and Pushmeet Kohli.

I spent summer 2013 at Microsoft Research Cambridge. Before my PhD, I worked as a Hardware Engineer at National Instruments and Guet.

 

Selected Publications

Abner Guzman-Rivera, Pushmeet Kohli, Ben Glocker, Jamie Shotton, Toby Sharp, Andrew Fitzgibbon and Shahram Izadi. Multi-Output Learning for Camera Relocalization. In Computer Vision and Pattern Recognition (CVPR), 2014 (Oral).
Abner Guzman-Rivera, Pushmeet Kohli, Dhruv Batra and Rob A. Rutenbar. Efficiently Enforcing Diversity in Multi-Output Structured Prediction. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2014 (Oral).
Abner Guzman-Rivera, Pushmeet Kohli and Dhruv Batra. DivMCuts: Faster Training of Structural SVMs with Diverse M-Best Cutting-Planes. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2013 (Oral).
Abner Guzman-Rivera, Dhruv Batra and Pushmeet Kohli. Multiple Choice Learning: Learning to Produce Multiple Structured Outputs. In Neural Information Processing Systems (NIPS), 2012.
Dhruv Batra, Payman Yadollahpour, Abner Guzman-Rivera and Greg Shakhnarovich. Diverse M-Best Solutions in Markov Random Fields. In European Conference in Computer Vision (ECCV), 2012 (Oral).
Jaesik Choi, Abner Guzman-Rivera and Eyal Amir. Lifted Relational Kalman Filtering. In International Joint Conference on Artificial Intelligence (IJCAI), 2011 (Oral).

 

Other Publications

Chuanjun Zhang, Glenn G. Ko, Jungwook Choi, Shang-nien Tsai, Minje Kim, Abner Guzman-Rivera, Rob A. Rutenbar, Paris Smaragdis, Mi Sun Park, Vijaykrishnan Narayanan, Hongyi Xin, Onur Mutlu, Bin Li, Li Zhao and Mei Chen. EMERALD: Characterization of emerging applications and algorithms for low-power devices. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2013.
Abner Guzman-Rivera, Pushmeet Kohli and Dhruv Batra. Faster Training of Structural SVMs with Diverse M-Best Cutting-Planes. In Discrete Optimization in Machine Learning Workshop (DISCML-NIPS), 2012.