Makhzani, Alireza

22 publications

ICML 2024 A Computational Framework for Solving Wasserstein Lagrangian Flows Kirill Neklyudov, Rob Brekelmans, Alexander Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani

ICML 2024 Can We Remove the Square-Root in Adaptive Gradient Methods? a Second-Order Perspective Wu Lin, Felix Dangel, Runa Eschenhagen, Juhan Bae, Richard E. Turner, Alireza Makhzani

ICML 2024 Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo Stephen Zhao, Rob Brekelmans, Alireza Makhzani, Roger Baker Grosse

NeurIPS 2024 Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding Daniel Severo, Ashish Khisti, Alireza Makhzani

ICML 2024 Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC Wu Lin, Felix Dangel, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard E. Turner, Alireza Makhzani

NeurIPSW 2023 A Computational Framework for Solving Wasserstein Lagrangian Flows Kirill Neklyudov, Rob Brekelmans, Alexander Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani

ICML 2023 Action Matching: Learning Stochastic Dynamics from Samples Kirill Neklyudov, Rob Brekelmans, Daniel Severo, Alireza Makhzani

ICML 2023 One-Shot Compression of Large Edge-Exchangeable Graphs Using Bits-Back Coding Daniel Severo, James Townsend, Ashish J Khisti, Alireza Makhzani

NeurIPSW 2023 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 E. Turner, Alireza Makhzani

NeurIPS 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

NeurIPSW 2022 Action Matching: A Variational Method for Learning Stochastic Dynamics from Samples Kirill Neklyudov, Daniel Severo, Alireza Makhzani

ICLR 2022 Improving Mutual Information Estimation with Annealed and Energy-Based Bounds Rob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg, Roger Baker Grosse, Alireza Makhzani

NeurIPSW 2021 Few Shot Image Generation via Implicit Autoencoding of Support Sets Andy Huang, Kuan-Chieh Wang, Guillaume Rabusseau, Alireza Makhzani

ICML 2021 Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding Yangjun Ruan, Karen Ullrich, Daniel S Severo, James Townsend, Ashish Khisti, Arnaud Doucet, Alireza Makhzani, Chris Maddison

ICLRW 2021 Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding Yangjun Ruan, Karen Ullrich, Daniel Severo, James Townsend, Ashish J Khisti, Arnaud Doucet, Alireza Makhzani, Chris J. Maddison

NeurIPS 2021 Variational Model Inversion Attacks Kuan-Chieh Wang, Yan Fu, Ke Li, Ashish Khisti, Richard S. Zemel, Alireza Makhzani

NeurIPSW 2021 Your Dataset Is a Multiset and You Should Compress It like One Daniel Severo, James Townsend, Ashish J Khisti, Alireza Makhzani, Karen Ullrich

ICML 2020 Evaluating Lossy Compression Rates of Deep Generative Models Sicong Huang, Alireza Makhzani, Yanshuai Cao, Roger Grosse

NeurIPSW 2020 Likelihood Ratio Exponential Families Rob Brekelmans, Frank Nielsen, Alireza Makhzani, Aram Galstyan, Greg Ver Steeg

NeurIPS 2017 PixelGAN Autoencoders Alireza Makhzani, Brendan J. Frey

NeurIPS 2015 Winner-Take-All Autoencoders Alireza Makhzani, Brendan J. Frey

ICLR 2014 K-Sparse Autoencoders Alireza Makhzani, Brendan J. Frey