Bulletin of the American Physical Society
APS March Meeting 2021
Volume 66, Number 1
Monday–Friday, March 15–19, 2021; Virtual; Time Zone: Central Daylight Time, USA
Session Y09: Quantum Machine LearningInvited Live
|
Hide Abstracts |
Sponsoring Units: DQI Chair: Yariv Yanay, Laboratory for Physical Sciences |
Friday, March 19, 2021 11:30AM - 12:06PM Live |
Y09.00001: Trainability of Quantum Neural Networks: Barren Plateaus and Scalability Invited Speaker: Patrick Coles Quantum neural networks (QNNs) have generated excitement around the possibility of efficiently analyzing quantum data. However, one of the key open questions is how well will QNNs scale. The past year has witnessed significant analytical progress on studying the scaling of gradients in QNNs. It was recently discovered that certain QNN architectures can exhibit exponentially vanishing gradients, known as barren plateau landscapes. This leads to exponential scaling in the required precision on the gradient, making the training process inefficient. Nevertheless, some techniques have been shown to avoid barren plateaus, such as correlating parameters, employing local cost functions, and keeping the circuit depth shallow. In this talk, we will discuss recent progress in understanding the barren plateau phenomenon in QNNs, focusing especially on analytical gradient scaling results for QNNs. |
Friday, March 19, 2021 12:06PM - 12:42PM Live |
Y09.00002: Which classes of functions can quantum machine learning models actually learn? Invited Speaker: Maria Schuld A lot of work in quantum machine learning focuses on how to practically train quantum models, or how to prove that they can be classically intractable. However, an important question is which types of functions they can actually express, and what we can conclude about their generalization power. This talk will give an overview of what we know about the types of models that generic quantum circuits represent, why they are theoretically very promising, but why they are not powerful just by virtue of being "quantum". |
Friday, March 19, 2021 12:42PM - 1:18PM Live |
Y09.00003: Applications and experimental realizations of quantum generative adversarial networks Invited Speaker: Seth Lloyd Quantum generative adversarial networks (qGANs) represent a potentially powerful quantum machine learning tool for the analysis of quantum data and quantum processes. This talk presents a review of the theory of quantum generative adversarial networks, describes their application to pattern recognition and to quantum state and process tomography, and summarizes the current experimental state of the art for implementing qGANs. We introduce a novel quantum generative network model based on the recently proposed quantum Wasserstein-1 distance. |
Friday, March 19, 2021 1:18PM - 1:54PM Live |
Y09.00004: Classical simulation of quantum circuits with neural-network states Invited Speaker: Giuseppe Carleo The vast majority of quantum states of interest for practical applications have distinctive features and intrinsic structure. These typically occupy only a very limited corner of the vast manifold of allowed quantum states, making them often amenable for compact classical representations. |
Friday, March 19, 2021 1:54PM - 2:30PM Live |
Y09.00005: Progress in Machine Learning with Tensor Networks Invited Speaker: Edwin Stoudenmire Tensor networks are well known to physicists in theoretical condensed matter and other areas of physics as a tool for solving strongly-correlated electron problems, but they are actually a general technique to compress large tensors, similar to low-rank factorizations of matrices. In recent years tensor networks have found diverse uses within applied mathematics, and some of these ideas are making their way back into physics again. After reviewing tensor networks, I will discuss recent progress in using them as a type of machine learning model, in contrast to neural networks or other model families. Tensor networks can give state of the art results, but what is most exciting is the progress in algorithm development and theory of machine learning that they make possible. |
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700