- Random cycle coding: lossless compression of cluster assignments via bits-back coding
Daniel Severo, Ashish Khisti, Alireza Makhzani
NeurIPS, 2024 - Probabilistic inference in language models via twisted sequential Monte Carlo
Stephen Zhao*, Rob Brekelmans*, Alireza Makhzani**, Roger Grosse**
ICML, 2024, (Best Paper Award) - Can we remove the square-root in adaptive gradient methods? a second-order perspective
Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard Turner, Alireza Makhzani
ICML, 2024 - Structured inverse-free natural gradient: memory-efficient & numerically-stable KFAC for large neural nets
Wu Lin*, Felix Dangel*, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard Turner, Alireza Makhzani
ICML, 2024, Also presented in NeurIPS Workshop on Optimization for Machine Learning, 2023 - A computational framework for solving Wasserstein Lagrangian flows
Kirill Neklyudov*, Rob Brekelmans*, Alexander Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani
ICML, 2024, Also presented in NeurIPS Workshop on Optimal Transport and Machine Learning, 2023 - Wasserstein quantum Monte Carlo: a novel approach for solving the quantum many-body Schrödinger equation
Kirill Neklyudov, Jannes Nys, Luca Thiede, Juan Carrasquilla, Qiang Liu, Max Welling, Alireza Makhzani
NeurIPS, 2023, (Spotlight) - Action matching: learning stochastic dynamics from samples
Kirill Neklyudov, Rob Brekelmans, Daniel Severo, Alireza Makhzani
ICML, 2023 - Random edge coding: one-shot bits-back coding of large labeled graphs
Daniel Severo, James Townsend, Ashish Khisti, Alireza Makhzani
ICML, 2023 - Compressing multisets with large alphabets using bits-back coding
Daniel Severo, James Townsend, Ashish Khisti, Alireza Makhzani, Karen Ullrich
IEEE Journal on Selected Areas in Information Theory, Special Issue on Modern Compression, 2023, Also presented in Data Compression Conference, 2021, (Oral Talk) - Quantum hypernetworks: training binary neural networks in quantum superposition
Juan Carrasquilla, Mohamed Hibat-Allah, Estelle Inack, Alireza Makhzani, Kirill Neklyudov, Graham Taylor, Giacomo Torlai
arXiv:2301.08292 (Submitted to Quantum), 2023 - Improving mutual information estimation with annealed and energy-based bounds
Rob Brekelmans*, Sicong Huang*, Marzyeh Ghassemi, Greg Ver, Roger Grosse, Alireza Makhzani
ICLR, 2022 - Variational model inversion attacks
Kuan-Chieh Wang, Yan Fu, Ke Li, Ashish Khisti, Richard Zemel, Alireza Makhzani
NeurIPS, 2021 - Your dataset is a multiset and you should compress it like one
Daniel Severo, James Townsend, Ashish Khisti, Alireza Makhzani, Karen Ullrich
NeurIPS Workshop on Deep Generative Models and Downstream Applications, 2021, (Best Paper Award) - Few shot image generation via implicit autoencoding of support sets
Andy Huang, Kuan-Chieh Wang, Guillaume Rabusseau, Alireza Makhzani
NeurIPS Workshop on Meta-Learning, 2021 - 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
ICML, 2021, (Long Oral Talk) - Likelihood ratio exponential families
Rob Brekelmans, Frank Nielsen, Alireza Makhzani, Aram Galstyan, Greg Steeg
NeurIPS Workshop on Deep Learning through Information Geometry, 2020 - Evaluating lossy compression rates of deep generative models
Sicong Huang*, Alireza Makhzani*, Yanshuai Cao, Roger Grosse
ICML, 2020, Also presented in NeurIPS Workshop on Bayesian Deep Learning, 2019, (Contributed Talk) - Implicit autoencoders
Alireza Makhzani
arXiv:1805.09804, 2018 - Unsupervised representation learning with autoencoders
Alireza Makhzani
PhD Thesis, University of Toronto (Canada), 2018 - Starcraft II: a new challenge for reinforcement learning
Oriol Vinyals, Timo Ewalds, Sergey Bartunov, Petko Georgiev, Alexander Vezhnevets, Michelle Yeo, Alireza Makhzani, Heinrich Küttler, John Agapiou, Julian Schrittwieser, others
arXiv:1708.04782, 2017 - Pixelgan autoencoders
Alireza Makhzani, Brendan Frey
NeurIPS, 2017 - Adversarial autoencoders
Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, Brendan Frey
ICLR Workshop, 2016 - Winner-take-all autoencoders
Alireza Makhzani, Brendan Frey
NeurIPS, 2015 - K-sparse autoencoders
Alireza Makhzani, Brendan Frey
ICLR, 2014 - Compressed sensing for jointly sparse signals
Alireza Makhzani
Masters Thesis, University of Toronto (Canada), 2012 - Distributed spectrum sensing in cognitive radios via graphical models
Alireza Makhzani, Shahrokh Valaee
5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2013 - Reconstruction of jointly sparse signals using iterative hard thresholding
Alireza Makhzani, Shahrokh Valaee
IEEE International Conference on Communications (ICC), 2012 - Reconstruction of a generalized joint sparsity model using principal component analysis
Alireza Makhzani, Shahrokh Valaee
IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2011