5. AI Systems Tübingen Meetup: Quantum & AI

We are happy to announce the 5th AI Systems Tübingen Meetup hosted by the University of Tübingen and IBM Research & Development. The topic of the meetup is "Quantum & AI". This time, we prepared three interesting talks for you:

1. Introduction to the world of quantum computing (Tristan Müller, IBM)
   This talk will give a brief introduction to quantum computing. It will also try to explain why everyone is talking about Quantum these days.

2. A rigorous and robust quantum speed-up in supervised machine learning (Kristan Temme, IBM)
   Over the past few years several quantum machine learning algorithms were proposed that promise quantum speed-ups over their classical counterparts. Most of these learning algorithms either assume quantum acce ss to data -- making it unclear if quantum speed-ups still exist without making these strong assumptions, or are heuristic in nature with no provable advantage over classical algorithms. In this paper, we establish a rigorous quantum speed-up for supervised classification using a general-purpose quantum learning algorithm that only requires classical access to data. Our quantum classifier is a conventional support vector machine that uses a fault-tolerant quantum computer to estimate a kernel function. Data samples are mapped to a quantum feature space and the kernel entries can be estimated as the transition amplitude of a quantum circuit. We construct a family of datasets and show that no classical learner can classify the data inverse-polynomially better than random guessing, assuming the widely-believed hardness of the discrete logarithm problem. Meanwhile, the quantum classifier achieves high accuracy and is robust against additive errors in the kernel entries that arise from finite sampling statistics.
   This is joint work with Yunchao Liu and Srinivasan Arunachalam

3. Hybrid combinatorial optimization on NISQ machines (Simon Garhofer, Uni TÜ)
   Quantum computers potentially provide a significant speedup in computing good approximations for optimal solutions of combinatorial optimization problems such as the Traveling Salesperson Problem and variations thereof. However, currently existing machines possess a fairly limited amount of qubits, such that they are hardly suitable for practically relevant problem instances. In this talk I'd like to illustrate an idea on how this gap might be bridged using classical algorithms for problem solving and machine learning.

Afterwards, we'll have a short virtual get-together.