[Qp-l] [QCSBP] Seminar today at 16:30 CET: Richard Küng

[Gilyén András]

Hi,

This is a friendly reminder that Richard Küng will speak this afternoon
about "The classical shadow formalism and (some) implications for quantum
machine learning". You can find the abstract of the talk at the bottom of
this email.

You can join using the following Zoom link:
https://berkeley.zoom.us/j/96826613566?pwd=MUZtOGllSklFM2d0NGhwaFBqNXhjdz09
(due to the default privacy settings you need to sign into your Zoom
account before joining).

After the seminar we will have room for informal discussions as well on
gather.town: https://gather.town/i/VDYwRBuy

Best,

András

2021.03.11 16:30 CET -- *Speaker: Richard Küng* (Johannes Kepler
University, Linz)

*Title:* The classical shadow formalism and (some) implications for quantum
machine learning

*Abstract:* Extracting important information from a quantum system as
efficiently and tractably as possible is an important subroutine in most
near-term applications of quantum hardware. We present an efficient method
for constructing an approximate classical description of a quantum state
using very few measurements of the state. This description, called a
classical shadow, can be used to predict many different properties. The
required number of measurements is independent of the system size and
saturates information-theoretic lower bounds. Subsequently, we combine
classical shadows with machine learning (ML). This combination showcases
that training data obtained from quantum experiments can be very empowering
for classical ML methods. More precisely, we study the complexity of
training classical and quantum ML models for predicting outcomes of
physical experiments. We prove that, a classical ML model can provide
accurate predictions on average by accessing measurement outcomes of
quantum experiments a number of times comparable to the optimal quantum ML
model. Exponential quantum ML advantages do, however, remain possible if we
insist on accurate worst-case prediction.

-- 
You received this message because you are subscribed to the Google Groups "Quantum CS Seminar" group.
To unsubscribe from this group and stop receiving emails from it, send an email to qcsseminar+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/qcsseminar/CAG54o1%3DgQuzA2wQ%2B_GtLsd8_Ezw883eAL-LBANa%2B%2BU7jxPhwXg%40mail.gmail.com.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://plc.inf.elte.hu/pipermail/qp-l/attachments/20210311/0f999753/attachment.html>