English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Recent work has demonstrated the utility of introducing non-linearity throughrepeat-until-success (RUS) sub-routines into quantum circuits for generativemodeling. As a follow-up to this work, we investigate two questions ofrelevance to the quantum algorithms and machine learning communities: Doesintroducing this form of non-linearity make the learning model classicallysimulatable due to the deferred measurement principle? And does introducingthis form of non-linearity make the overall model's training more unstable?With respect to the first question, we demonstrate that the RUS sub-routines donot allow us to trivially map this quantum model to a classical one, whereas amodel without RUS sub-circuits containing mid-circuit measurements could bemapped to a classical Bayesian network due to the deferred measurementprinciple of quantum mechanics. This strongly suggests that the proposed formof non-linearity makes the model classically in-efficient to simulate. In thepursuit of the second question, we train larger models than previously shown onthree different probability distributions, one continuous and two discrete, andcompare the training performance across multiple random trials. We see thatwhile the model is able to perform exceptionally well in some trials, thevariance across trials with certain datasets quantifies its relatively poortraining stability.

A supplemental investigation of non-linearity in quantum generative models with respect to simulatability and optimization