Sequential Generative Models: Some Basics & Advances. @ Generative modelling summer school, June 2023
Make Stein's Method "Great Again" for Generative modelling? @ Distance-based methods for machine learning workshop, June 2023 [video]
Introduction to Bayesian Neural Networks. @ ProbAI 2023 summer school, June 2023
Towards Causal Deep Generative Models for Sequential Data. @ Quarter on Causality "When Causal Inference Meets Statistical Analysis", Apr 2023
Variational Bayes for Deep Learning: Towards Function-Space Uncertainty Quantification. @ BayesComp, Mar 2023
Understanding Masked Pre-Training: Fundamentally Different? @ GenU 2022 workshop, Sept 2022
Introduction to Bayesian Neural Networks. @ ProbAI 2022 summer school, June 2022 [video][notes][demo1][demo2]
Inference with scores: slices, diffusions and flows. @ ICML 2021 INNF+ workshop, July 2021 [video]
EBM inference & learning: A personal story. @ ICLR 2021 EBM workshop, May 2021 [video] [panel]
From parametric models to Gaussian processes. @ UnderstandingDL talk series, Data @ University de Sao Paolo, Apr 2021 [video]
Understanding approximate inference in Bayesian neural networks: A joint talk. Mar 2021 (as moderator).
Advances in Approximate Inference. Tutorial @ NeurIPS 2020
On estimating epistemic uncertainty. @ NeurIPS 2019 Bayesian deep learning workshop, Dec 2019 [video]
How accurate is the uncertainty estimate from your Bayesian neural networks? @ MICCAI 2019 UNSURE workshop, Oct 2019
Bayesian neural networks: a function space view tour. @ Gaussian process summer school, Sept 2019 [video]
Gradient estimators for implicit models with Stein's method. @ ICML 2019 Stein's method workshop, June 2019 [video]
Variational implicit processes. @ ICML 2019, June 2019
On KL divergence and beyond. @ U Cambridge Faculty of English, Nov 2018
Meta-learning for stochastic gradient MCMC. @ UAI 2018 uncertainty in DL workshop, Aug 2018
Efficient computation for Bayesian deep learning. @ MSR Cambridge & Oxford statistics, Mar 2018
Gradient estimators for implicit models. @ NIPS 2017 approximate inference workshop, Dec 2017
Wild approximate inference: why and how. @ UCL CSML seminar series, Dec 2017
Adversarial attacks and defences. @ AI safety reading group, CUED, Nov 2017
Approximate inference with amortised MCMC. @ ICML 2017 implicit generative model workshop, Aug 2017
Dropout-alpha BNNs. @ ICML 2017, Aug 2017
Approximate inference with amortised MCMC. CamAIML workshop, Mar 2017
Objective functions for variational auto-encoders. @ Twitter Cortex Vx (previously Magic Pony), Sept 2016
Variational inference with Rényi divergence. MSR-MLG joint workshop, Mar 2016
Alpha divergence back to conversation. Research Talk @ CBL, Feb 2016
Towards a unified variational framework for approximate Bayesian inference. Invited talk @ Tsinghua University, Dec 2015
Stochastic expectation propagation. Spotlight @ NIPS 2015, Dec 2015
Stochastic optimisation and adaptive learning rates. Reading Group Talk @ CBL (with Mark Rowland), Nov 2015 [code]
Concave-convex procedure. Tea Talk @ CBL, Oct 2015
Expectation propagation as a way of life. Tea Talk @ CBL, Feb 2015. [reference]
Introduction to transfer learning. Reading Group Talk @ CBL (with Pei-Hao Su), Jan 2015.
Bayesian learning for restricted Boltzmann machines. Research Talk @ CBL, Nov 2014.
On Restricted Boltzmann Machine Learning. Guest Talk @ Dept of Math, SYSU, Jun 2014.
Loopy Belief Propagation. RCC Talk @ CBL (with Alex Matthews), Apr 2014.
The Importance of Encoding. Tea Talk @ CBL, Feb 2014. [reference]
IT & ML: Channels, Quantizers, and Divergences. RCC Talk @ CBL (with Antonio Artés-Rodríguez), Jan 2014.