Accelerating generative models and nonconvex optimisation (ONLINE)

Accelerating generative models and nonconvex optimisation (ONLINE)

This workshop will focus on theoretical and methodological challenges related to generative models and optimisation.

By The Alan Turing Institute

Date and time

Fri, 24 Mar 2023 02:30 - 09:30 PDT

Location

Online

Agenda

9:30 AM - 9:35 AM

Welcome

Ioannis Kosmidis

9:40 AM - 10:20 AM

Generative modelling of extremes with neural networks

Emmanuel Gobet, Ecole Polytechnique, France

We investigate new parametrizations based on neural networks in order to approximate and sample multi-variate extreme values, especially in the case of heavy-tailed distributions. We discuss two appr...

10:25 AM - 11:10 AM

Interacting Particle Systems for EM

Tim Johston, University of Edinburgh

Francesca Crucinio, ENSAE, France

In this talk we discuss a new interacting particle system used for implementing an expectation maximization (EM) procedure (or more generally, to optimize over the parameters of a latent variable mod...

11:10 AM - 11:25 AM

Coffee break

11:30 AM - 12:10 PM

Improving the variational learning of physics driven neural generative models

Arnaud Vadeboncoeur, University of Cambridge

Parametric PDEs are ubiquitous in engineering practice. Being able to solve these problems efficiently is of great interest to engineers for model calibration, iterative design, and UQ. In this talk ...

12:15 PM - 12:30 PM

DiffusionJAX

Benjamin Boys, University of Cambridge

DiffusionJAX is an open-sourced python package for verifying and applying new research in diffusion modelling, a high-dimensional sampling framework that is developing at a fast pace. In particular, ...

12:30 PM - 1:25 PM

Lunch break

1:30 PM - 2:15 PM

From denoising diffusion models to transport for generative modelling and infe

Arnaud Doucet, Oxford University

Denoising diffusion models are a novel powerful class of techniques for generative modelling and inference. We will introduce these methods and present some of their limitations. We will then discuss...

2:15 PM - 3:00 PM

Langevin Monte-Carlo: Randomised mid-point method revisited

Arnak Dalalyan, ENSAE, France

Langevin Monte Carlo is an efficient and widely used method for generating random samples from a given target distribution in a high-dimensional Euclidean space. Various variants of the Langevin Mont...

3:00 PM - 3:15 PM

Coffee break

3:20 PM - 4:05 PM

Convergence of denoising diffusion models under the manifold hypothesis

Valentin de Bortoli, CNRS, France

Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. Such models approximate the time-reversal of a forward noising...

4:05 PM - 4:30 PM

Closing remarks

Deniz Akyildiz

Sotirios Sabanis

About this event

About the event

Generative models have dominated the AI scene with their impressive performance while their precise theoretical and algorithmic understanding is still unclear. This workshop will act as the follow-up workshop of the Theory and Methods Challenges Fortnight on "Accelerating Generative Models and Nonconvex Optimisation" and will focus on theoretical and methodological challenges related to generative models and optimisation, solutions to some of those challenges, and exciting future directions on the foundations of generative models. The workshop will also act as a vehicle for broad engagement with the Data Science and AI community worldwide on the theory and applications of generative models.

The event will have a mixture of talks and software demos that were developed by a team of researchers from around the world during the Theory and Methods Challenge Fortnight event that took place in June and September 2022.

International speakers that contributed to the TMCF challenge and others have been invited including Arnaud Doucet, Arnak Dalalyan and Emmanuel Gobet; please find the final programme below.

This event will be delivered in hybrid format, there is a limit of 45 in-person tickets for this event. If you would like to attend in-person, please reserve your place here.

For those attending online please make sure to register using the access link under 'Location'.

Organisers:

Dr Deniz Akyildiz, Lecturer at Imperial College London, UK.

Professor Sotirios Sabanis, Turing Fellow and University of Edinburgh, UK and NTU Athens, Greece.

If you require further information please email tmcf@turing.ac.uk

Currently, there is a call for new challenges, more information on the call webpage.

This workshop is part of the AI UK 2023 Fringe Events hosted by The Alan Turing Institute.

Organised by

The Alan Turing Institute

The Alan Turing Institute is the national institute for data science and artificial intelligence.

Sales Ended