Folgen
Alireza Makhzani
Alireza Makhzani
Research Scientist, Google DeepMind
Bestätigte E-Mail-Adresse bei google.com - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Adversarial autoencoders
A Makhzani, J Shlens, N Jaitly, I Goodfellow, B Frey
International Conference on Learning Representations (ICLR) 2016 Workshop, 2015
3663*2015
Starcraft II: A new challenge for reinforcement learning
O Vinyals, T Ewalds, S Bartunov, P Georgiev, AS Vezhnevets, M Yeo, ...
arXiv preprint arXiv:1708.04782, 2017
12272017
k-Sparse Autoencoders
A Makhzani, B Frey
International Conference on Learning Representations (ICLR) 2014, 2014
556*2014
Winner-take-all autoencoders
A Makhzani, BJ Frey
Neural Information Processing Systems (NeurIPS) 2015, 2015
3362015
Variational model inversion attacks
KC Wang, Y Fu, K Li, A Khisti, R Zemel, A Makhzani
Neural Information Processing Systems (NeurIPS) 2021, 2021
1372021
Pixelgan autoencoders
A Makhzani, BJ Frey
Neural Information Processing Systems (NeurIPS) 2017, 2017
1322017
Action Matching: Learning Stochastic Dynamics from Samples
K Neklyudov, R Brekelmans, D Severo, A Makhzani
International Conference on Machine Learning (ICML) 2023, 2023
512023
A winner-take-all method for training sparse convolutional autoencoders
A Makhzani, B Frey
NIPS deep learning workshop, 2014
452014
Improving lossless compression rates via monte carlo bits-back coding
Y Ruan, K Ullrich, DS Severo, J Townsend, A Khisti, A Doucet, ...
International Conference on Machine Learning (ICML) 2021 (Long Oral Talk), 2021
322021
Implicit autoencoders
A Makhzani
arXiv preprint arXiv:1805.09804, 2018
312018
Evaluating Lossy Compression Rates of Deep Generative Models
S Huang, A Makhzani, Y Cao, R Grosse
International Conference on Machine Learning (ICML) 2019, 2019
302019
Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo
S Zhao, R Brekelmans, A Makhzani, R Grosse
International Conference on Machine Learning (ICML) 2024 (Best Paper Award), 2024
252024
Unsupervised representation learning with autoencoders
A Makhzani
PhD Thesis, University of Toronto (Canada) 2018, 2018
202018
A computational framework for solving Wasserstein Lagrangian flows
K Neklyudov, R Brekelmans, A Tong, L Atanackovic, Q Liu, A Makhzani
International Conference on Machine Learning (ICML) 2024, 2024
152024
Compressing Multisets with Large Alphabets using Bits-Back Coding
D Severo, J Townsend, A Khisti, A Makhzani, K Ullrich
IEEE Journal on Selected Areas in Information Theory (Special Issue on …, 2022
15*2022
Improving mutual information estimation with annealed and energy-based bounds
R Brekelmans, S Huang, M Ghassemi, GV Steeg, R Grosse, A Makhzani
International Conference on Learning Representations (ICLR) 2022, 2022
152022
Reconstruction of jointly sparse signals using iterative hard thresholding
A Makhzani, S Valaee
IEEE International Conference on Communications (ICC) 2012, 2012
152012
Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation
K Neklyudov, J Nys, L Thiede, J Carrasquilla, Q Liu, M Welling, ...
Neural Information Processing Systems (NeurIPS) 2023 (Spotlight Talk), 2023
122023
Distributed spectrum sensing in cognitive radios via graphical models
A Makhzani, S Valaee
IEEE International Workshop on Computational Advances in Multi-Sensor …, 2013
122013
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective
W Lin, F Dangel, R Eschenhagen, J Bae, RE Turner, A Makhzani
International Conference on Machine Learning (ICML) 2024, 2024
102024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20