Random cycle coding: lossless compression of cluster assignments via bits-back coding Alireza Makhzani NeurIPS, 2024
Probabilistic inference in language models via twisted sequential Monte Carlo Alireza Makhzani **, Roger Grosse**ICML, 2024 , (Best Paper Award)
Can we remove the square-root in adaptive gradient methods? a second-order perspective Alireza Makhzani ICML, 2024
Structured inverse-free natural gradient: memory-efficient & numerically-stable KFAC for large
neural nets Alireza Makhzani ICML, 2024 ,
Also presented in NeurIPS Workshop on Optimization for Machine Learning, 2023
A computational framework for solving Wasserstein Lagrangian flows 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 Alireza Makhzani NeurIPS, 2023 , (Spotlight)
Action matching: learning stochastic dynamics from samples Alireza Makhzani ICML, 2023
Random edge coding: one-shot bits-back coding of large labeled graphs Alireza Makhzani ICML, 2023
Compressing multisets with large alphabets using bits-back coding Alireza Makhzani , Karen UllrichIEEE 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 Alireza Makhzani , Kirill Neklyudov, Graham
Taylor, Giacomo TorlaiarXiv:2301.08292 (Submitted to Quantum), 2023
Improving mutual information estimation with annealed and energy-based bounds Alireza Makhzani ICLR, 2022
Variational model inversion attacks Alireza Makhzani NeurIPS, 2021
Your dataset is a multiset and you should compress it like one Alireza Makhzani , Karen UllrichNeurIPS Workshop on Deep Generative Models and Downstream Applications, 2021 ,
(Best Paper Award)
Few shot image generation via implicit autoencoding of support sets Alireza Makhzani NeurIPS Workshop on Meta-Learning, 2021
Improving lossless compression rates via Monte Carlo bits-back coding Alireza Makhzani , Chris MaddisonICML, 2021 , (Long Oral Talk)
Likelihood ratio exponential families Alireza Makhzani , Aram Galstyan, Greg SteegNeurIPS Workshop on Deep Learning through Information Geometry, 2020
Evaluating lossy compression rates of deep generative models Alireza Makhzani *, Yanshuai Cao, Roger GrosseICML, 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 Alireza Makhzani , Heinrich Küttler, John Agapiou, Julian Schrittwieser, othersarXiv:1708.04782, 2017
Pixelgan autoencoders Alireza Makhzani , Brendan FreyNeurIPS, 2017
Adversarial autoencoders Alireza Makhzani , Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, Brendan FreyICLR Workshop, 2016
Winner-take-all autoencoders Alireza Makhzani , Brendan FreyNeurIPS, 2015
K-sparse autoencoders Alireza Makhzani , Brendan FreyICLR, 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 Valaee5th 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 ValaeeIEEE International Conference on Communications (ICC), 2012
Reconstruction of a generalized joint sparsity model using principal component analysis Alireza Makhzani , Shahrokh ValaeeIEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP),
2011