Colloquium: Tensor Network Machine Learning Models

Date

Jun 18, 2018

Time

4:30 PM - 5:30 PM

Speaker

Dr. Edwin Miles Stoudenmire

Affiliation

Flatiron Institute, Center for Computational Quantum Physics, New York, USA

Series

MPI-PKS Kolloquium

Language

en

Main Topic

Physik

Other Topics

Physik

Description

Tensor networks are an efficient representation of interesting many-body wavefunctions and underpin powerful algorithms for strongly correlated systems. But tensor networks could be applied much more broadly than just for representing wavefunctions. Large tensors similar to wavefunctions appear naturally in certain families of models studied extensively in machine learning. Decomposing the model parameters as a tensor network leads to interesting algorithms for training models on real-world data which scale better than existing approaches. In addition to training models directly for recognizing labeled data, tensor network real-space renormalization approaches can be used to extract statistically significant "features" for subsequent learning tasks. I will also highlight other benefits of the tensor network approach such as the flexibility to blend different approaches and to interpret trained models.

Last modified: Jun 18, 2018, 2:07:11 AM