Tensor Networks for Generative Modeling From Boltzmann machines to - PowerPoint PPT Presentation

Tensor Networks for Generative Modeling From Boltzmann machines to Born machines, and back ang ( �� ) Lei W https://wangleiphy.github.io Institute of Physics, Beijing Han, Wang, Fan, LW, Zhang, PRX18’ Chen, Cheng, Xie, LW, Xiang, PRB 18’ Chinese Academy of Sciences Cheng, Chen, LW, Entropy 18’+unpublished

TNSAA: Live long and prosper Ψ Quantum circuits Neural networks and architecture and parametrization Probabilistic graphical models

TNSAA in the era of quantum computing Simulation and validation of Noise-resilient quantum circuits quantum circuits with TNS architecture Villalonga et al, 1811.09599 Kim and Swingle, 1711.07500 | 0 i | 0 i = · · · ψ i +1 ψ i | 0 i | 0 i + quantum tomography, quantum annealing, quantum error correction, holographic duality, and more

TNSAA in the era of deep learning Hidden Markov Model p ( h t | h t − 1 ) … Hidden p ( o t | h t ) Observation • Widely used in speech recognition, bioinformatics, cryptography… • Learning, inference, and sampling algorithms (Forward-backward message passing, Viterbi, Baum-Welch) => Think of positive MPS Temme, Verstraete,1003.2545 Critch, Morton, 1210.2812 Tensor Graphical Networks Models Zhao, Jaeger, Neural Comput. 2010 Bailly, J. Mach. Learn. Res. 2011 Robeva, Seigal, 1710.01437 Chen, Cheng, Xie, LW, Xiang, 1701.04831

Unleash the power of tensor network states and algorithms for generative modeling

Discriminative and generative learning y = f ( x ) p ( x , y ) p ( y | x ) or

Discriminative and generative learning “What I can not create, I do not understand”

Generated Arts $432,500 25 October 2018 Christie’s New York https://www.christies.com/Features/A-collaboration-between-two-artists-one-human-one-a-machine-9332-1.aspx

Generated Arts Gaussian Generative Noise Network $432,500 25 October 2018 Christie’s New York https://www.christies.com/Features/A-collaboration-between-two-artists-one-human-one-a-machine-9332-1.aspx

Generate Molecules Latent Physical attributes configurations Generate Simple Complex Distributions Distribution Inference Sanchez-Lengeling & Aspuru-Guzik, Science 2018

<latexit sha1_base64="l+MU6Wop3O4gDLGg4JnxmuonPhM=">ACEHicbVDNSsNAGNzUv1r/oj16WSxCvZREBPVW9OKxgrGFNpTNZtMu3WzC7kYaQp7CB/Cqj+BJvPoGPoGv4abNwbYOLDvMfB/fMF7MqFSW9W1U1tY3Nreq27Wd3b39A/Pw6FGicDEwRGLRM9DkjDKiaOoYqQXC4JCj5GuN7kt/O4TEZJG/EGlMXFDNOI0oBgpLQ3NOoybAy9ivkxD/WXT/AwOzYbVsmaAq8QuSQOU6AzNn4Ef4SQkXGpOzbVqzcDAlFMSN5bZBIEiM8QSPS15SjkEg3m4XP4alWfBhEQj+u4Ez9u5GhUBbh9GSI1Fgue4X4n9dPVHDlZpTHiSIczw8FCYMqgkUT0KeCYMVSTRAWVGeFeIwEwkr3tXBFTYtoMq/pZuzlHlaJc96bln3F432TVlRFRyDE9AENrgEbXAHOsABGKTgBbyCN+PZeDc+jM/5aMUod+pgAcbXL/rwnUs=</latexit> <latexit sha1_base64="l+MU6Wop3O4gDLGg4JnxmuonPhM=">ACEHicbVDNSsNAGNzUv1r/oj16WSxCvZREBPVW9OKxgrGFNpTNZtMu3WzC7kYaQp7CB/Cqj+BJvPoGPoGv4abNwbYOLDvMfB/fMF7MqFSW9W1U1tY3Nreq27Wd3b39A/Pw6FGicDEwRGLRM9DkjDKiaOoYqQXC4JCj5GuN7kt/O4TEZJG/EGlMXFDNOI0oBgpLQ3NOoybAy9ivkxD/WXT/AwOzYbVsmaAq8QuSQOU6AzNn4Ef4SQkXGpOzbVqzcDAlFMSN5bZBIEiM8QSPS15SjkEg3m4XP4alWfBhEQj+u4Ez9u5GhUBbh9GSI1Fgue4X4n9dPVHDlZpTHiSIczw8FCYMqgkUT0KeCYMVSTRAWVGeFeIwEwkr3tXBFTYtoMq/pZuzlHlaJc96bln3F432TVlRFRyDE9AENrgEbXAHOsABGKTgBbyCN+PZeDc+jM/5aMUod+pgAcbXL/rwnUs=</latexit> <latexit sha1_base64="l+MU6Wop3O4gDLGg4JnxmuonPhM=">ACEHicbVDNSsNAGNzUv1r/oj16WSxCvZREBPVW9OKxgrGFNpTNZtMu3WzC7kYaQp7CB/Cqj+BJvPoGPoGv4abNwbYOLDvMfB/fMF7MqFSW9W1U1tY3Nreq27Wd3b39A/Pw6FGicDEwRGLRM9DkjDKiaOoYqQXC4JCj5GuN7kt/O4TEZJG/EGlMXFDNOI0oBgpLQ3NOoybAy9ivkxD/WXT/AwOzYbVsmaAq8QuSQOU6AzNn4Ef4SQkXGpOzbVqzcDAlFMSN5bZBIEiM8QSPS15SjkEg3m4XP4alWfBhEQj+u4Ez9u5GhUBbh9GSI1Fgue4X4n9dPVHDlZpTHiSIczw8FCYMqgkUT0KeCYMVSTRAWVGeFeIwEwkr3tXBFTYtoMq/pZuzlHlaJc96bln3F432TVlRFRyDE9AENrgEbXAHOsABGKTgBbyCN+PZeDc+jM/5aMUod+pgAcbXL/rwnUs=</latexit> Probabilistic Generative Modeling p ( x ) How to express, learn, and sample from a high-dimensional probability distribution ? �� “random” images “natural” images ��

Tensor Networks for Generative Modeling From Boltzmann machines to - PowerPoint PPT Presentation

Tensor Networks for Generative Modeling From Boltzmann machines to Born machines, and back ang ( ) Lei W https://wangleiphy.github.io Institute of Physics, Beijing Han, Wang, Fan, LW, Zhang, PRX18 Chen, Cheng, Xie, LW, Xiang, PRB

Conditional Generative Adversarial Networks (and a brief look at image-to-image translation)

Generative networks part 2: GANs 23 / 54 Recap on generative networks Generative networks provide

Generative Adversarial Networks Ian Goodfellow Research Scientist GPU Technology Conference

Generative Adversarial Networks (GANs) Ian Goodfellow, OpenAI Research Scientist Presentation at

Generative Adversarial Networks Aaron Mishkin UBC MLRG 2018W2 1 Generative Adversial Networks

Generative Adversarial Networks (GANs) Ian Goodfellow, OpenAI Research Scientist Re-Work Deep

Generative Adversarial Networks (GANs) Ian Goodfellow, Research Scientist MLSLP Keynote, San

Generative Adversarial Networks (GANs) Ian Goodfellow, OpenAI Research Scientist Presentation at

CSC321 Lecture 19: Generative Adversarial Networks Roger Grosse Roger Grosse CSC321 Lecture 19:

Towards Compositional and Generative Tensor Optimizations Adilla Susungi 1 , Norman A. Rink 2 ,

Generative Adversarial Networks (GANs) Ian Goodfellow, OpenAI Research Scientist NIPS 2016

Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes with Deep Generative

Tensor Networks And The ITensor Library E.M. Stoudenmire Jan 2019 - MIT Flatiron Institute

Generative Adversarial Networks presented by Ian Goodfellow presentation co-developed with Aaron

Models through Tensor Networks 2019.12.04 Naoki KAWASHIMA (ISSP) Tensor Network (TN) (1)

Introduction: Generative Model for Graphs Modeling graphs is fundamental for studying networks

Improved dose determination for Molecular Radiotherapy Andrew Robinson Dave Cullen Nuclear

Adaptive Management: Applying What We Learn Sriju Sharma, Associate Director - Monitoring,

20 December 2018 Sharing on School Matters Sharing on School Matters School Programmes School

A Tutorial on Tablet PC Simon Fraser University CMPT 354 Fall 2007 Agenda Tablet PC Overview

Generative Adversarial Networks Stefano Ermon, Aditya Grover Stanford University Lecture 9

Issues with the Federal Government Lewis Roca Rothgerber Christie 1 PANEL Moderator

Mental Health Awareness for Spiritual Companions 25 th and 26 th March, Glastonbury Sarah Jane

Planning for Success Multidisciplinary Approach and Common Pitfalls Vicki Ibrahim Director of