Center for Advanced Intelligence Project

Date and Time:
August 13th, 2024 13:30 – 17:00(JST)
Venue: Online and Open Space at the RIKEN AIP Nihonbashi office*
*The Open Space; AIP researchers are only available.

Program:

13:30-14:15 Hachem Kadri
Title: Quantum Machine Learning
Abstract:
Quantum Machine learning is an emerging field of research, with fast growth. This research field is largely driven by the desire to develop artificial intelligence that uses quantum technologies to improve the speed and performance of learning algorithms. In this talk, I will start by giving a brief introduction to the field of Quantum Machine Learning showing different types of interactions between machine learning and quantum computing and information. I will then illustrate these interactions by discussing quantum extensions of linear regression and perceptron algorithms.

14:15-15:00 Enrico Rinaldi
Title: Parameter estimation from quantum-jump data using neural networks
Abstract:
We introduce a neural network-based method for estimating parameters of a quantum probe monitored through continuous measurement. Unlike traditional methods focusing on diffusive signals from weak measurements, our approach uses quantum correlations in photon-counting data with quantum jumps. We compare the precision of our method to Bayesian inference, known for optimal information retrieval. Through numerical experiments on a two-level quantum system, we show that our method achieves similar performance to Bayesian inference but with much lower computational costs. Additionally, our method is robust against imperfections in measurement and training data. This technique is efficient for quantum parameter estimation with photon-counting data, useful for quantum sensing, quantum imaging, and laboratory calibration tasks.

15:00-15:30 Break

15:30-16:15 Hayata Yamasaki
Title: Advantage of Quantum Machine Learning from General Computational Advantages
Abstract:
An overarching milestone of quantum machine learning (QML) is to demonstrate the advantage of QML over all possible classical learning methods in accelerating a common type of learning task as represented by supervised learning with classical data. However, the provable advantages of QML in supervised learning have been known so far only for the learning tasks designed for using the advantage of specific quantum algorithms, i.e., Shor’s algorithms. Here we explicitly construct an unprecedentedly broader family of supervised learning tasks with classical data to offer the provable advantage of QML based on general quantum computational advantages, progressing beyond Shor’s algorithms. Our learning task is feasibly achievable by executing a general class of functions that can be computed efficiently in polynomial time for a large fraction of inputs by arbitrary quantum algorithms but not by any classical algorithm. We prove the hardness of achieving this learning task for any possible polynomial-time classical learning method. We also clarify protocols for preparing the classical data to demonstrate this learning task in experiments. These results open routes to exploit a variety of quantum advantages in computing functions for the experimental demonstration of the advantage of QML.
The talk is based on the following preprint.
https://arxiv.org/abs/2312.03057

16:15-17:00 Discussion

Bio

Hachem Kadri is Professor of Computer Science in LIS, CNRS, Aix-Marseille University (AMU), France. He is the head of the Data Science Department at AMU and the Vice President-elect of the French Machine Learning Society SSFAM. He was the head of the Machine Learning group at AMU from 2018 to 2020. He is interested in theoretical machine learning, with a special emphasis on kernel methods, statistical learning, functional data analysis, tensor models and quantum machine learning. His work has appeared in top-tier AI and ML journals and conferences, including JMLR, NeurIPS, ICML and AISTATS. He is the PI of a JCJC Starting Grant research project, QuantML, funded by the French National Research Agency (ANR) and devoted to the foundations of quantum machine learning algorithms. He was the co-organizer of the ICML’12 workshop on “Object, Functional and Structured Data: Towards Next Generation Kernel-based Methods” and the ECML’22 workshop on “Quantum Machine Learning”. He was the program co-chair of 18th Francophone Conference on Machine Learning (CAP’16).

Enrico Rinaldi is a computational physicist in the Applied Quantum Algorithms team at Quantinuum K.K. . He is also a Visiting Scientist at RIKEN participating in the research activities of various centers like iTHEMS, RQC, and CPR. He is also a member of the SQAI Center of Innovation. He holds a Ph.D. in theoretical particle physics from the University of Edinburgh, and during his career he held various research positions at different National Laboratories in the US and Japan, where he studied Lattice Gauge Theory using large scale simulations on TOP500 supercomputers, from the study of dark matter to nuclear interactions and quantum gravity. In Quantinuum he works at the intersection of machine learning and quantum algorithms, to advance research in high energy physics, nuclear physics, quantum control, and error mitigation. Recently he collaborated on the random circuit sampling project with the global Quantinuum team that released the new H2-1 quantum computer with 56 qubits.

Hayata Yamasaki is an assistant professor at the University of Tokyo (2022-present) and also a director (principal investigator) leading the theory research team of Quantum Foundation and Innovation Center at Nanofiber Quantum Technologies (NanoQT), Inc (2024-present). His research is on quantum machine learning, quantum computation, quantum algorithms, computational complexity theory, numerical techniques for the analyses of quantum mechanics, computational architectures for building quantum computers, quantum error correction, quantum information theory, and their applications.

All participants are required to agree with the AIP Seminar Series Code of Conduct.
Please see the URL below.
https://aip.riken.jp/event-list/termsofparticipation/?lang=en

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.