Amar Shah CBL

About Me Amar has a BIG smile when he's happy

I am a doctoral candidate studying in the Machine Learning Group at the University of Cambridge, supervised by Zoubin Ghahramani and advised by Carl Edward Rasmussen.

I joined MLG in 2012 after working as a Quantitative Strategist at Goldman Sachs for 2 years. Previous to this I received a MMath and a BA in Mathematics from the University of Cambridge.

My current research interests include probabilistic deep modelling and its application to problems involving a trade off between exploration and exploitation including active learning and Bayesian optimization.


Research Visits

NASA Frontier Development Lab
Summer 2016
frontierdevelopmentlab.org
Montreal Institute for Learning Algorithms
Fall 2015
mila.umontreal.ca

Publications

Pareto Frontier Learning with Expensive Correlated Objectives [pdf]
Amar Shah, Zoubin Ghahramani
International Conference on Machine Learning, 2016
Unitary Evolution Recurrent Neural Networks [pdf]
Martin Arjovsky, Amar Shah, Yoshua Bengio
International Conference on Machine Learning, 2016
Predictive Entropy Search for Multi-objective Bayesian Optimization [pdf]
Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Amar Shah, Ryan P. Adams
International Conference on Machine Learning, 2016
Markov Beta Processes for Time Evolving Dictionary Learning [pdf]
Amar Shah, Zoubin Ghahramani
Uncertainty in Artificial Intelligence, 2016
Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Functions [pdf]
Amar Shah, Zoubin Ghahramani
Neural Information Processing Systems, 2015
An Empirical Study of Stochastic Variational Algorithms for the Beta Bernoulli Process [pdf]
Amar Shah, David A. Knowles, Zoubin Ghahramani
International Conference on Machine Learning, 2015
Student-t Processes as Alternatives to Gaussian Processes [pdf]
Amar Shah, Andrew G. Wilson, Zoubin Ghahramani
Artificial Intelligence and Statistics, 2014
Discovering Latent Influence in Online Social Activities via Shared Cascade Poisson Processes [pdf]
Tomohura Iwata, Amar Shah, Zoubin Ghahramani
ACM Knowledge Discovery and Data Mining, 2013
Determinantal Clustering Processes - A Nonparametric Bayesian Approach to Kernel Based Semi-Supervised Clustering [pdf]
Amar Shah, Zoubin Ghahramani
Uncertainty in Articficial Intelligence, 2013

Workshop Papers

Bayesian Optimization using Student-t Processes [pdf]
Amar Shah, Andrew G. Wilson, Zoubin Ghahramani
Bayesian Optimization, Neural Information Processing Systems, 2013

Contact

Email Cambridge logo

Cambridge University Engineering Department Cambridge logo
Trumpington Street
Cambridge
CB2 1PZ
United Kingdom