Semantic Information Pursuit for Multimodal Data Analysis
Lead Research Organisation:
University College London
Department Name: Computer Science
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
Publications
Tse, L
(2018)
Graph Cut Segmentation Methods Revisited with a Quantum Algorithm
in IJQI
Sun S
(2022)
Stability-based PAC-Bayes analysis for multi-view learning algorithms
in Information Fusion
Rocchetto A
(2018)
Learning hard quantum distributions with variational autoencoders
in npj Quantum Information
Pérez-Ortiz M
(2022)
Network topological determinants of pathogen spread.
in Scientific reports
Guedj B
(2020)
Kernel-Based Ensemble Learning in Python
in Information
Grant E
(2018)
Hierarchical quantum classifiers
in npj Quantum Information
Donini M
(2019)
Combining heterogeneous data sources for neuroimaging based diagnosis: re-weighting and selecting what is important.
in NeuroImage
Bulathwela S
(2020)
SUM'20: State-based User Modelling
| Description | Key finding 1: Adversarial learning is one of the most successful approaches to modelling high-dimensional probability distributions from data. The quantum computing community has recently begun to generalise this idea and to look for potential applications. We derived an adversarial algorithm for the problem of approximating an unknown quantum state. Although this could be done on universal (large) quantum computers, the adversarial formulation enables us to execute the algorithm on near-term quantum computers. Key finding 2: Quantum mechanics fundamentally forbids deterministic discrimination of quantum states and processes. However, the ability to optimally distinguish various classes of quantum data is an important primitive in quantum information science. We trained quantum circuits to distinguish quantum states and provided an example of machine learning in the quantum setting for a task that has inherently no classical analogue. Key finding 3: Quantum circuits with hierarchical structure have been used to perform binary classification of classical data encoded in a quantum state. We demonstrated that more expressive circuits in the same family achieve better accuracy and can be used to classify highly correlated quantum states, for which there is no known efficient classical method. Key finding 4: We showed that DNF formulae can be quantum PAC-learned in polynomial time under product distributions using a quantum example oracle. The best classical algorithm (without access to membership queries) runs in superpolynomial time. Key finding 5: The number of parameters describing a quantum state is well known to grow exponentially with the number of particles. This scaling clearly limits our ability to do tomography to systems with no more than a few qubits and has been used to argue against the universal validity of quantum mechanics itself. However, from a computational learning theory perspective, it can be shown that, in a probabilistic setting, quantum states can be approximately learned using only a linear number of measurements. We experimentally demonstrate this linear scaling in optical systems with up to 6 qubits. |
| Exploitation Route | Further research. |
| Sectors | Digital/Communication/Information Technologies (including Software) |
| Description | Graph Parameters and Physical Correlations: from Shannon to Connes, via Lovász and Tsirelson |
| Form Of Engagement Activity | A magazine, newsletter or online publication |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Article in ERCIM news |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://ercim-news.ercim.eu/en112/special/graph-parameters-and-physical-correlations-from-shannon-to... |
| Description | ICML Tutorial |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Benjamin Guedj and I gave a tutorial on A Primer on PAC-Bayesian Learning at ICML 2019 one of the two premier conferences in machine learning and artificial intelligence. It was attended by approximately 750 people and was streamed live to a wider audience, see https://icml.cc/Conferences/2019/ScheduleMultitrack?event=4338. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://icml.cc/Conferences/2019/ScheduleMultitrack?event=4338 |
| Description | NeurIPS Tutorial |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Other audiences |
| Results and Impact | It was an invited tutorial at the premier machine learning conference, Neural Information Processing Systems held in December 2018 in Montreal. The audience was over 500 researchers and professional practitioners from industry and business. |
| Year(s) Of Engagement Activity | 2018 |
| URL | https://www.youtube.com/watch?v=m8PLzDmW-TY |