Agenda for the Data Centric Engineering Reading Group

Alan Turing Institute, UK

For more information about the reading group, or to join the mailing list, contact Marina Riabiz, FX Briol or Chris Oates.

For more information about the Data Centric Engineering programme, visit https://www.turing.ac.uk/research/research-programmes/data-centric-engineering

=============================================================

Optimization

=============================================================

06/02/19: Stochastic Gradient Descent (Marina Riabiz)

13/02/19: Proof of convergence rate of Stochastic Gradient Descent (Ömer Deniz Akyıldız)

20/02/19: Proof of convergence rate of Gradient Descent (Ömer Deniz Akyıldız)

27/02/19: Stochastic Gradient Langevin Dynamics (Andrew Duncan)

06/03/2019: Conjugate Gradient Methods (Taha Ceriti)

Extra References:

=============================================================

Gaussian Processes and RKHS

=============================================================

13/03/19: Hyperparameter estimation for Gaussian Processes (Alex Diaz)

20/03/19: Gaussian Interpolation/Regression Error Bounds (George Wynne)

27/03/19: Structure of the Gaussian RKHS (Toni Karvonen)

Extra References:

Steinwart, I., Hush, D., & Scovel, C. (2006). An explicit description of the reproducing kernel Hilbert spaces of Gaussian RBF kernels. IEEE Transactions on Information Theory, 52(10), 4635–4643

=============================================================

Invited Talks + Deep GPs

=============================================================

03/04/19: Bayesian synthetic likelihood (Leah South)

12/04/19: Deep Gaussian Processes (Kangrui Wang)

17/04/19: Multi Level Monte Carlo (Alastair Gregory)

24/04/19: Adaptive Bayesian Quadrature (Matthew Fisher)

=============================================================

MMD & Stein’s method

=============================================================

01/05/19: Controlling Convergence with Maximum Mean Discrepancy (Chris Oates)

08/05/19: Introduction to Stein’s method (FX Briol)

15/05/19: Bochner's Theorem and Maximum Mean Discrepancy (George Wynne)

Extra References:

https://sites.google.com/site/steinsmethod/home

=============================================================

Greedy Algorithms

=============================================================

19/06/19: Convergence Guarantees for Adaptive Bayesian Quadrature Methods (Motonobu Kanagawa)

=============================================================

Uncertainty Exploration in Aerospace

=============================================================

26/06/19: Using machine learning to predict and understand turbulence modelling uncertainties (Ashley Scillitoe)

03/07/19: Polynomial approximations in uncertainty quantification (Pranay Seshadri)

=============================================================

Bayesian Learning and Algorithms

=============================================================

10/07/19: A Kernel Stein Test for Comparing Latent Variable Models (Heishiro Kanagawa)

17/07/19: Multi-resolution Multi-task Gaussian Processes (Oliver Hamelijnck)

24/07/19: A Primer on PAC Bayesian Learning (Benjamin Guedj)

=============================================================

Gradient Flows

=============================================================

31/07/19: An Introduction to Measure Transport (Chris Oates)

06/08/19: Gradient Flows for Statistical Computation (Marina Riabiz)

14/08/19: The Mathematics of Gradient Flows (Andrew Duncan)

14/08/19: Displacement Convexity and Implications for Variational Inference (Andrew Duncan)

=============================================================

Estimators for Intractable Models

=============================================================

23/08/19: Comparing spatial models in the presence of spatial smoothing (Earl Duncan)

28/08/19: Fisher efficient inference of intractable models (Song Liu)

04/09/19: Statistical Inference for Generative Models with Maximum Mean Discrepancy (FX Briol)

=============================================================

Uncertainty Quantification and Probabilistic Numerics

=============================================================

11/09/19: A New Approach to Probabilistic Rounding Error Analysis (Jon Cockayne)

25/09/19: TBC (David Green)

09/10/19: The Ridgelet Transform and a Quadrature of Neural Networks (Takuo Matsubara)

=============================================================

PAC Bayes

=============================================================

16/10/19: TBC (Omar Rivasplata)