Alireza Makhzani

Faculty Member

Adjunct Professor, Department of Electrical & Computer Engineering, Faculty of Applied Science & Engineering, University of Toronto

Canada CIFAR Artificial Intelligence Chair

Alireza completed his PhD in Electrical & Computer Engineering at the University of Toronto in 2017 where he was a student under Brendan Frey and part of the Machine Learning group. He has a broad set of interests in machine learning, but his most recent research focuses on generative models and their applications in semi-supervised learning; neural networks that can learn sparse representations of data; and deep reinforcement learning algorithms. During his PhD, he interned for the Google Brain Team in 2015 where he worked on generative models of images; and Google DeepMind in 2016 where he worked on developing deep reinforcement learning algorithms for the StarCraft II game. Alireza completed his Master’s at the University of Toronto in 2012 and received his Bachelor’s degree from Amirkabir University of Technology (Tehran Polytechnic) in Iran in 2010.

Research Interests

  • Generative Models
  • Reinforcement Learning

Publications

Improving lossless compression rates via monte carlo bits-back coding

Yangjun Ruan and Karen Ullrich and Daniel S Severo and James Townsend and Ashish Khisti and Arnaud Doucet and Alireza Makhzani and Chris Maddison

2021

Variational Model Inversion Attacks

Kuan-Chieh Wang and Yan Fu and Ke Li and Ashish Khisti and Richard Zemel and Alireza Makhzani

2021

Few Shot Image Generation via Implicit Autoencoding of Support Sets

Andy Huang and Kuan-Chieh Wang and Guillaume Rabusseau and Alireza Makhzani

2021

Improving Mutual Information Estimation with Annealed and Energy-Based Bounds

Rob Brekelmans and Sicong Huang and Marzyeh Ghassemi and Greg Ver Steeg and Roger Baker Grosse and Alireza Makhzani

2021

Your Dataset is a Multiset and You Should Compress it Like One

Daniel Severo and James Townsend and Ashish J Khisti and Alireza Makhzani and Karen Ullrich

2021