QuEnG Seminar - Quantum algorithms for supervised and unsupervised machine learning

on the January 3, 2019

At 2:00pm
As part of the QuEnG Seminar - Computer Science, we are pleased to welcome Alessandro Luongo who is doing a thesis at Paris Diderot on quantum machine learning.
Abstract
I'll present the main tools used in quantum machine learning: procedures to perform quantum linear algebraic operations, the QRAM circuit as an access model on the data, and routines to calculate distances - which we refined. Among the results of our group, I'll present three new algorithms. The first, QSFA is a dimensionality reduction algorithm that maps the dataset in a lower dimensional space, where classification can be performed with higher accuracy. Dimensionality reduction is often a necessary while performing classification in high dimensional spaces due to the curse of dimensionality. The second is QFD, a supervised classifier which assign a new point to the cluster with minimum average square distance between the vector and the points of the cluster. The third is q-means: the quantum version of k-means. Being an iterative algorithm for clustering, q-means has convergence and precision guarantees similar to the classical variants of $k$-means. All the algorithms presented here are poly-logarithmic in the number of vectors in the dataset, thus with an exponential separation with respect to classical algorithms.


ACCESS:
If you want to attend the seminar and don't usually have access to the LIG building send an email to Richard EAST indicating your name and laboratory or organization so that your details may be forwarded to the reception in advance. They will then be able to let you in on the day.


Published on December 25, 2018

Practical informations

Lieu(x)


Laboratoire d'Informatique de Grenoble (LIG)
Room 406
25 Avenue des Martyrs, 38000 Grenoble