About The Forum
Calendar 2017 Poster Sessions : Boosted Generative Models
Abstract:
We propose a new approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner that permits likelihood evaluation, including recent latent variable models. Further, our approach allows the ensemble to include discriminative models trained to distinguish real data from model-generated data. We show theoretical conditions under which incorporating a new model in the ensemble will improve the fit and empirically demonstrate the effectiveness of boosting on density estimation and sample generation on synthetic and benchmark real datasets.
Bio:
Aditya Grover is a Ph.D student in Computer Science at Stanford University working with Stefano Ermon. Aditya is broadly interested in advancing the theory and applications of machine learning and general artificial intelligence. His current research focusses on designing and analyzing scalable algorithms for unsupervised learning and inference in generative models. His research honors include the Microsoft Research Ph.D Fellowship (2017), the best paper award at the international workshop on statistical relational artificial intelligence (2016) and the best undergraduate theses project award from Indian Institute of Technology Delhi (2015).
We propose a new approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner that permits likelihood evaluation, including recent latent variable models. Further, our approach allows the ensemble to include discriminative models trained to distinguish real data from model-generated data. We show theoretical conditions under which incorporating a new model in the ensemble will improve the fit and empirically demonstrate the effectiveness of boosting on density estimation and sample generation on synthetic and benchmark real datasets.
Bio:
Aditya Grover is a Ph.D student in Computer Science at Stanford University working with Stefano Ermon. Aditya is broadly interested in advancing the theory and applications of machine learning and general artificial intelligence. His current research focusses on designing and analyzing scalable algorithms for unsupervised learning and inference in generative models. His research honors include the Microsoft Research Ph.D Fellowship (2017), the best paper award at the international workshop on statistical relational artificial intelligence (2016) and the best undergraduate theses project award from Indian Institute of Technology Delhi (2015).