COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

University of Cambridge > Talks.cam > CQIF Seminar > Quantum Expectation Maximization and algorithms for learning representations

## Quantum Expectation Maximization and algorithms for learning representationsAdd to your list(s) Download to your calendar using vCal - Alessandro Luongo (IRIF, Paris)
- Thursday 21 November 2019, 12:00-13:00
- MR15, Centre for Mathematical Sciences, Wilberforce Road, Cambridge.
If you have a question about this talk, please contact Sathyawageeswar Subramanian. The Expectation-Maximization (EM) algorithm is a fundamentaltool in unsupervised machine learning. It is often used as an efficientway to solve Maximum Likelihood (ML) and Maximum A Posteriori (MAP)estimation problems, especially for models with latent variables. It isalso the algorithm of choice to fit mixture models. In this talk wedefine and use a quantum version of EM to fit a Gaussian MixtureMode (GMM). We start by introducing in great detail all the tools usedin quantum machine learning (QRAM, distance estimation procedures,quantum linear algebra, etc.). Then we present q-means: a quantumalgorithm for k-means. We generalize q-means algorithm to fit a GMM . Ouralgorithms are only polylogarithmic in the number of elements in thetraining set, but are polynomial in other parameters – as the dimensionof the feature space and the number of components in the mixture. We’lldiscuss some experiments concerning the runtime of these algorithms onreal datasets. We conclude by analyzing prospect relations betweenquantum iterative algorithms and the Information Bottleneck Method. This talk is part of the CQIF Seminar series. ## This talk is included in these lists:- All CMS events
- CMS Events
- CQIF Seminar
- DAMTP info aggregator
- Interested Talks
- MR15, Centre for Mathematical Sciences, Wilberforce Road, Cambridge
- bld31
Note that ex-directory lists are not shown. |
## Other listsDAMTP Departmental Seminar Meeting the Challenge of Healthy Ageing in the 21st Century Slavonic Studies Graduate Research Forum## Other talksFluid dynamics in superhydrophobic channels structured with micro scale grooves Conceptual and methodological advances in laminar fMRI Horizontal & vertical categorification: from monoids to bicategories 1 million correlations: steps towards reproducible psychological science Towards a new global earthquake catalogue - Full waveform constraints on earthquake mechanisms and their uncertainty Politics of Hybridisation (Domestication Practices across History) |