I am a faculty member at the Vector Institute for Artificial Intelligence, an associate professor (status-only) in the Department of Electrical & Computer Engineering at the University of Toronto, and a Canada CIFAR AI Chair. I have a broad set of interests within machine learning, but recently I am working on
- Deep Generative Models (in particular Diffusion Models)
- Alignment / Inference / Reasoning in Large Language Models
- Variational Inference and Monte Carlo Methods
- Optimization Methods for Neural Networks
- Computational Optimal Transport
- Intersection of Machine Learning with Information Theory
I completed my PhD (thesis) at the University of Toronto with Brendan Frey in 2017, where I was part of the Machine Learning Group. During my PhD, I interned for Google DeepMind in 2016, where I worked on developing deep reinforcement learning algorithms for the StarCraft II game (AlphaStar project); and Google Brain in 2015, where I developed Adversarial Autoencoders. I completed my Masters (thesis) at the University of Toronto in 2012, and received my Bachelor’s degree from Amirkabir University of Technology, Iran, in 2010.
Office: Vector Institute, MaRS Centre
Email: makhzani AT vectorinstitute DOT ai
Selected Publications
- A computational framework for solving Wasserstein Lagrangian flows
Kirill Neklyudov*, Rob Brekelmans*, Alexander Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani
NeurIPS Workshop on Optimal Transport and Machine Learning, 2023 - Action matching: learning stochastic dynamics from samples
Kirill Neklyudov, Rob Brekelmans, Daniel Severo, Alireza Makhzani
International Conference on Machine Learning (ICML), 2023 - Improving mutual information estimation with annealed and energy-based bounds
Rob Brekelmans*, Sicong Huang*, Marzyeh Ghassemi, Greg Ver, Roger Grosse, Alireza Makhzani
International Conference on Learning Representations (ICLR), 2022 - Improving lossless compression rates via Monte Carlo bits-back coding
Yangjun Ruan*, Karen Ullrich*, Daniel Severo*, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris Maddison
International Conference on Machine Learning (ICML), 2021, (Long Talk) - Evaluating lossy compression rates of deep generative models
Sicong Huang*, Alireza Makhzani*, Yanshuai Cao, Roger Grosse
International Conference on Machine Learning (ICML), 2020, Also presented in NeurIPS Workshop on Bayesian Deep Learning, 2019, (Contributed Talk) - Adversarial autoencoders
Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, Brendan Frey
International Conference on Learning Representations (ICLR) Workshop, 2016