DeepMind/ELLIS CSML Seminar Series

The Computational Statistics and Machine Learning (CSML) Lunch Time Seminars present a range of talks representing the diverse interests of CSML. The talks range from invited external speakers to PhD and postdoc presentations designed to foster collaboration between the large number of machine learning and statistics researchers in CSML.

Talks will usually be held on Fridays from 2pm to 3pm in the Roberts Building G08 Sir David Davies LT on Zoom. PhD students and postdocs of CS, Statistics and Gatsby departments are particularly encouraged to attend.

If available, slides from previous talks can be found from the relevant event page (for example, slides from Ozan Oktem's talk are available here). You can also find a folder with all previous slides here.

The CSML seminar series is kindly sponsored by DeepMind.

AI Centre: Jean Kaddour & Antonin Schrab & Robert Kirk
Gatsby: Ilyes Khemakhem
Statistics: Fredrik Hallgren

If you would like to be added to the mailing list for seminar and other CSML announcements, complete the request form here.

Usual time: Friday, 14:00 - 15:00
Location (unless otherwise noted): Zoom
iCalendar URL:

Upcoming Events

Fri, 28 May 14:00 - 15:00 Zoom Adji Bousso Dieng (Princeton University): Adversarial Learning for Probabilistic Modeling

Previous Events

Fri, 12 Mar 2021 Petar Veličković (DeepMind): A Tale of Three Implicit Planners and the XLVIN agent
Fri, 05 Mar 2021 Nicholas Bishop (University of Southampton): Strategic Least Squares Regression with Verified Training Data
Fri, 26 Feb 2021 Greg Yang (Microsoft Research): Feature Learning in Infinite-Width Neural Networks
Fri, 19 Feb 2021 Chelsea Finn (Stanford University): Principles for Tackling Distribution Shift: Pessimism, Adaptation, and Anticipation
Fri, 12 Feb 2021 David Duvenaud (University of Toronto): Latent Stochastic Differential Equations: An Unexplored Model Class.
Fri, 05 Feb 2021 Mihaela van der Schaar (University of Cambridge): Why medicine is creating exciting new frontiers for machine learning
Fri, 29 Jan 2021 Guido Montufar (Max Planck Institute for Mathematics in the Sciences): Implicit bias of gradient descent for mean squared error regression with wide neural networks
Fri, 22 Jan 2021 Marta Garnelo (DeepMind): Meta-Learning and Neural Processes
Fri, 15 Jan 2021 Jakob Foerster (Facebook): Zero-Shot (Human-AI) Coordination (in Hanabi) and Ridge Rider
Fri, 08 Jan 2021 Sergey Levine (UC Berkeley): Data-Driven Reinforcement Learning: Deriving Common Sense from Past Experience
Fri, 18 Dec 2020 Luigi Gresele & Giancarlo Fissore (MPI for Intelligent Systems & Inria Paris-Saclay): Relative gradient optimization of the Jacobian term in unsupervised deep learning
Fri, 04 Dec 2020 Jonathan Frankle (MIT): The Lottery Ticket Hypothesis: On Sparse, Trainable Neural Networks
Fri, 27 Nov 2020 Alexey Dosovitskiy (Google Brain): Non-convolutional architectures for recognition and generation
Thu, 09 Apr 2020 Maurice Weiler (University of Amsterdam): Equivariant Neural Networks
Thu, 27 Feb 2020 Aude Genevay (MIT): Learning with entropy-regularized optimal transport
Fri, 10 Jan 2020 Catalina Cangea (University of Cambridge): Question Answering in Realistic Visual Environments: Challenges and Approaches
Thu, 28 Nov 2019 NeurIPS Previews 2019
Fri, 15 Nov 2019 Varun Kanade (University of Oxford): Implicit Regularization for Optimal Sparse Recovery
Fri, 11 Oct 2019 Arthur Mensch (Ecole Normale Superieure (ENS) Paris): Geometric Losses for Distributional Learning
Fri, 28 Jun 2019 Benjamin Guedj (UCL - INRIA): A primer on PAC-Bayesian learning with applications to deep neural networks
Fri, 21 Jun 2019 Marc Deisenroth (Imperial College): Faster Learning and Richer Models for the Next AI Challenges
Fri, 07 Jun 2019 Victor Prisacariu (University of Oxford): (Deep-ish) SLAM for Next Generation AR
Thu, 30 May 2019 Quentin Berthet (University of Cambridge): Optimal transport methods in statistics and machine learning: theory and applications
Thu, 09 May 2019 Umut Şimşekli (Télécom ParisTech): Nonparametric Generative Modeling via Optimal Transport and Diffusions with Provable Guarantees
Fri, 26 Apr 2019 Nicolas Anastassacos (UCL): Investigating the Emergence of Cooperative Behaviour for Artificial Societies with RL
Fri, 08 Mar 2019 Sanjeevan Ahilan (UCL, Gatsby): Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning
Fri, 01 Mar 2019 Sander Dieleman (DeepMind): Generating music in the raw audio domain
Fri, 22 Feb 2019 Tengyao Wang (UCL): Sparse PCA: statistical and computational trade-offs
Fri, 01 Feb 2019 Ozan Öktem (Cambridge University/KTH): Deep learning for Bayesian inverse problems from tomography
Fri, 25 Jan 2019 Dino Sejdinovic (University of Oxford): Learning on Aggregate Outputs with Kernels
Fri, 18 Jan 2019 Sesh Kumar (Imperial College): Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
Fri, 11 Jan 2019 Jean-Baptiste Alayrac (DeepMind): Weakly Supervised Learning from Videos
Fri, 14 Dec 2018 Ricardo Pio Monti (UCL (Gatsby)): Causal discovery with general non-linear relationships using non-linear ICA
Fri, 30 Nov 2018 Artur Garcez (City University): Logic Tensor Networks: A System for Deep Learning with Symbolic Reasoning
Fri, 23 Nov 2018 Various (UCL, DeepMind, Imperial): NIPS Previews
Fri, 16 Nov 2018 Kayvan Sadeghi (UCL): Probabilistic Independence, Graphs, and Random Networks
Fri, 19 Oct 2018 Kai Arulkumaran (Imperial College): Tutorial on Deep RL
Fri, 08 Jun 2018 Edward Grefenstette (DeepMind): Learning to follow grounded language instructions in the "real" world
Fri, 01 Jun 2018 Piotr Mirowski (DeepMind): Learning to Navigate
Fri, 25 May 2018 Marco Cuturi (CREST-ENSAE/Université Paris-Saclay): Regularization for Optimal Transport and Dynamic Time Warping Distances
Fri, 27 Apr 2018 Stefanos Zafeiriou (Imperial College London): Discovering correlations in the modern era: robust and deep learning approaches
Fri, 20 Apr 2018 Lucas Theis (Twitter): Evaluating generative models
Fri, 13 Apr 2018 Seth Flaxman (Imperial College): Predictor Variable Prioritization in Nonlinear Models: A Genetic Association Case Study
Fri, 09 Mar 2018 Sam Livingstone (UCL Statistical Science): What we talk about when we talk about non-reversible MCMC
Fri, 23 Feb 2018 Ricardo Silva (UCL Statistical Science): Some Machine Learning Tools to Aid Causal Inference
Fri, 16 Feb 2018 Zbigniew Wojna (UCL): Architectures for big scale 2D imagery
Fri, 09 Feb 2018 Sebastian Nowozin (Microsoft Research): Opportunities and Challenges in Generative Adversarial Networks – Looking beyond the Hype
Fri, 02 Feb 2018 Maria Lomeli (University of Cambridge): Kernel Monte Carlo estimators for partial rankings
Fri, 26 Jan 2018 Edouard Oyallon (CentraleSupelec): Invariance & invertibility in CNNs
Fri, 12 Jan 2018 Tamara Fernandez (UCL Gatsby): A Gaussian process model for survival analysis
Fri, 15 Dec 2017 Dougal Sutherland (UCL, Gatsby): Efficient score estimation with infinite-dimensional exponential families
Fri, 08 Dec 2017 Relja Arandjelovic (DeepMind): Look, Listen and Learn
Fri, 01 Dec 2017 Yingzhen Li (University of Cambridge): Wild approximate inference: why and how
Fri, 24 Nov 2017 Various (UCL): NIPS Accepted Papers
Fri, 17 Nov 2017 Mark van der Wilk (University of Cambridge): Convolutional Gaussian processes
Fri, 03 Nov 2017 Aapo Hyvarinen (UCL, Gatsby): Nonlinear ICA using temporal structure: a principled framework for unsupervised deep learning
Fri, 20 Oct 2017 Hugh Salimbeni (Imperial College London): Doubly Stochastic Variational Inference for Deep Gaussian Processes
Fri, 27 Jan 2017 Mijung Park (Amsterdam Machine Learning Lab): Variational Bayes In Private Settings (VIPS)
Fri, 02 Dec 2016 Various (UCL): NIPS Previews
Fri, 25 Nov 2016 Theo Trouillon (Xerox Research, Univ. Grenoble Alpes): Complex-Valued Embeddings for Knowledge Base Completion
Fri, 18 Nov 2016 Ryota Tomioka (Microsoft Research Cambridge): f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Fri, 11 Nov 2016 Daniel Tarlow (Microsoft Research Cambridge): Learning to Code: Machine Learning for Program Induction
Fri, 04 Nov 2016 Remi Munos (Google DeepMind): Safe and efficient off-policy reinforcement learning
Fri, 28 Oct 2016 Shakir Mohamed (Google DeepMind): Building Machines that Imagine and Reason: Principles and Applications of Deep Generative Models
Wed, 26 Oct 2016 Hrishi Aradhye (Google Research/ Google Play): Personalized app/games recommendations on Google Play using machine learning
Wed, 19 Oct 2016 Iasonas Kokkinos (UCL): Deeplab to UberNet: from task-specific to task-agnostic deep learning in computer vision
Wed, 29 Jun 2016 Wolfgang Gatterbauer (CMU): Approximate lifted inference with probabilistic databases
Fri, 10 Jun 2016 Andrew Fitzgibbon (Microsoft Research Cambridge): Lifting, VarPro, ICP, and all that.
Wed, 01 Jun 2016 Yee-Whye Teh (University of Oxford): Distributed Bayesian Learning
Fri, 06 May 2016 Ted Meeds (University of Amsterdam): Likelihood-free Inference by Controlling Simulator Noise
Fri, 22 Apr 2016 Ingmar Schuster (Université Paris-Dauphine): Kernel Sequential Monte Carlo
Fri, 15 Apr 2016 Chris Oates (University of Technology Sydney): Stein Operators on Hilbert Spaces
Thu, 24 Mar 2016 David Silver (Google DeepMind, University College London): AlphaGO: Mastering the game of Go with deep neural networks and tree search
Fri, 18 Mar 2016 Emtiyaz Khan (EPFL): Approximate Bayesian Inference: Bringing Statistics, Optimization, and Machine Learning Together.
Fri, 11 Mar 2016 Francois-Xavier Briol (University of Warwick): Probabilistic Numerics Approaches to Integration
Fri, 04 Mar 2016 James Hensman (Lancaster University): Variational Inference in Gaussian Process Models
Fri, 19 Feb 2016 Thore Graepel (DeepMind, University College London): DeepMind's Quest for Artificial General Intelligence: From Atari to AlphaGo and beyond
Fri, 04 Dec 2015 Stephen Pasteris, Wittawat Jitkrittum, Ricardo Silver (UCL): NIPS previews
Fri, 27 Nov 2015 Tom Schaul (Google Deepmind): Universal Value Function Approximators
Fri, 20 Nov 2015 Shakir Mohamed (Google Deepmind): Memory-based Bayesian Reasoning with Deep Learning
Fri, 13 Nov 2015 Yarin Gal (University of Cambridge ): Modern Deep Learning through Bayesian Eyes
Fri, 16 Oct 2015 Roberto Calandra (TU Darmstadt): Bayesian Modeling for Optimization and Control in Robotics
Fri, 28 Aug 2015 Elad Hazan (Princeton University): Classification with Low Rank and Missing Data
Fri, 24 Jul 2015 Ribana Roscher (Freie Universität Berlin): Discriminative and Reconstructive Methods for Classification of Remote Sensing Images
Mon, 29 Jun 2015 Manik Varma (Microsoft Research India): Extreme Classification: A New Paradigm for Ranking & Recommendation
Fri, 29 May 2015 Javier Gonzalez (University of Sheffield): Batch Bayesian Optimization via Local Penalization
Fri, 15 May 2015 Zhenwen Dai (University of Sheffield): Variational Hierarchical Community of Experts
Fri, 08 May 2015 Patrick Conrad (University of Warwick): Probability Measures on Numerical Solutions of ODEs and PDEs for Uncertainty Quant. and Inference
Fri, 17 Apr 2015 Csaba Szepesvari (University of Alberta, Canada): Optimistic Algorithms for Online Learning in Structured Decision Problems
Fri, 10 Apr 2015 Seppo Virtanen (University of Warwick): Non-parametric Bayes to infer playing strategies adopted in a population of mobile gamers
Fri, 27 Mar 2015 Adrian Weller (University of Cambridge): Recent results on the Bethe approximation
Fri, 20 Mar 2015 Iain Murray (Edinburgh University): Flexible and deep models for density estimation
Fri, 13 Mar 2015 Peter Sollich (King's College, University Of London): Gaussian process regression on graphs
Fri, 06 Mar 2015 Heiko Strathmann (covering co-author Mark Girolami who cannot make it) (Gatsby Unit, UCL): Unbiased Bayes for Big Data: Paths of Partial Posteriors
Wed, 04 Mar 2015 Jason Weston (Facebook, New York): Memory Networks
Fri, 27 Feb 2015 Matt Hoffmann (University Of Cambridge): Predictive Entropy Search
Fri, 06 Feb 2015 Peter Tino (University of Birmingham): Learning from Temporal Data Using Dynamical Feature Space
Fri, 23 Jan 2015 Vladimir Vovk (Royal Holloway University of London): Probabilistic prediction in machine learning
Fri, 16 Jan 2015 Kamil Ciosek (UCL, Computer Science): Combining state abstraction and temporal abstraction in MDP solving
Fri, 05 Dec 2014 Andrew McDonald, Kacper Chwialkowski, Balaji Lakshminarayanan (UCL/Gatsby): NIPS Previews
Fri, 28 Nov 2014 Stephen Roberts (Oxford University): Planets, Pulsars, People and Petabytes: Explorations of Machine Learning in Astronomy
Fri, 21 Nov 2014 Amos Storkey (Edinburgh University): Series Expansion Methods for Approximate Learning, Filtering and Smoothing in Diffusions
Fri, 14 Nov 2014 Ata Kaban (University of Birmingham): Learning with random projections
Fri, 07 Nov 2014 Chris Williams (Edinburgh University): Switching Linear Dynamical Systems for Condition Monitoring in the Intensive Care Unit
Fri, 17 Oct 2014 Peter Flach (University of Bristol): Comparing apples and oranges -- reinterpreting common evaluation metrics in classification
Fri, 12 Sep 2014 Remi Munos (INRIA Lille): Two generic principles in modern bandits: the optimistic principle and Thompson sampling
Thu, 19 Jun 2014 Gerhard Neumann (TU Darmstadt): Learning Modular Control Policies in Robotics
Fri, 13 Jun 2014 David Barber, Kacper Chwiałkowski, Dino Sejdinovic (UCL): ICML preview talks
Fri, 23 May 2014 Remi Bardenet (Deptartment of Statistics, Oxford): Scaling up MCMC: a subsampling approach
Fri, 16 May 2014 Chris Watkins (Royal Holloway University of London): Evolution as a standard Monte-Carlo algorithm
Fri, 09 May 2014 Demis Hassabis (Google DeepMind): General Artificial Intelligence
Fri, 02 May 2014 Zoltan Szabo (UCL, Gatsby): Distribution Regression - the Set Kernel Heuristic is Consistent
Fri, 25 Apr 2014 Alex Graves (Google Deepmind): Generating Sequences with Recurrent Neural Networks
Fri, 11 Apr 2014 Dimitrios Athanasakis (UCL): Principled Non-Linear Feature Selection (with applications in representation learning)
Fri, 04 Apr 2014 Sarah Chisholm (UCL, Computer Science): Statistical Methods for Analysing Time Series Data of Animal Movement
Fri, 21 Mar 2014 Lloyd Elliott (UCL, Gatsby): Bayesian nonparametric dynamic-clustering and genetic imputation
Fri, 14 Mar 2014 Srini Turaga (Gatsby Unit & Wolfson Institute for Biomedical Research): Using ConvNets, MALIS and crowd-sourcing to map the retinal connectome.
Fri, 07 Mar 2014 Robert Stojnic (Cambridge Systems Biology Centre): Bayesian Molecular LEGO
Fri, 28 Feb 2014 Trevor Cohn (University of Sheffield): Language processing using Gaussian Processes
Fri, 21 Feb 2014 Marc Deisenroth (Imperial College, London): Statistical Machine Learning for Autonomous Systems
Fri, 14 Feb 2014 Peter Forbes (Oxford, Department of Statistics): Quantifying Fingerprint Evidence using Bayesian Alignment
Fri, 24 Jan 2014 Ioanna Manolopoulou (UCL, Statistics): Diffusion modelling of motion trajectories under the influence of covariates
Fri, 10 Jan 2014 Stephen Pasteris (UCL, Computer Science): Online Similarity Prediction of Networked Data
Fri, 29 Nov 2013 Alfredo Kalaitzis, Bernadino Romero Paredes, Dino Sejdinovic (UCL): NIPS preview talks
Fri, 22 Nov 2013 Mario Marchand (Universite Laval): Risk Bounds and Learning Algorithms for the Regression Approach to Structured Output Prediction
Fri, 15 Nov 2013 Thore Graepel (Microsoft Research Cambridge and Chair of Machine Learning, Department of Computer Science, UCL): Private traits and attributes are predictable from digital records of human behavior
Fri, 01 Nov 2013 Sam Livingstone (UCL, Statistics): Diffusions with position-dependent volatility and the Metropolis-adjusted Langevin algorithm
Fri, 10 May 2013 Isadora Antoniano-Villalobos (Department of Decision Sciences, Bocconi University, Italy): Bayesian inference for nonparametric mixture models with intractable normalizing constants
Fri, 26 Apr 2013 Chris Bracegirdle (UCL (CS)): Probabilistic Inference for Changepoints and Cointegration
Fri, 05 Apr 2013 Robert Jenssen (University of Tromso, Norway): Entropy-Relevant Dimensions in Kernel Feature Space
Fri, 22 Mar 2013 Vladimir Krylov (UCL): Extraction of geometrical objects from images with MCMC methods
Fri, 08 Mar 2013 David Silver (UCL): Reinforcement Learning and Simulation-Based Search
Fri, 01 Mar 2013 Tamara Broderick (University of California, Berkeley): Feature allocations, probability functions, and paintboxes
Fri, 22 Feb 2013 Matthew Higgs (UCL): A Population Approach to Ubicomp System Design (APAUSD)
Fri, 08 Feb 2013 Gary Macindoe (UCL): A hybrid Cholesky decomposition algorithm for multicore CPUs with GPU accelerators
Fri, 25 Jan 2013 Andriy Mnih (UCL): A fast and simple algorithm for training neural probabilistic language models
Fri, 11 Jan 2013 Ed Challis (UCL): Variational approximate inference in linear latent variable models
Thu, 29 Nov 2012 Juan Carlos Martinez-Ovando (Banco de México): Non- and semi-parametric construction of stationary dependent models
Fri, 23 Nov 2012 Ben Calderhead and Simon Byrne (UCL): The use of geometry in MCMC
Fri, 09 Nov 2012 Steffen Grunewalder (UCL): Conditional Expectation Estimates for Discrete Control
Fri, 26 Oct 2012 Dino Sejdinovic (UCL): Equivalence of distance-based and RKHS-based statistics in hypothesis testing
Fri, 12 Oct 2012 Jan Gasthaus (UCL): Hierarchical Bayesian Nonparametric Models for Sequences
Fri, 28 Sep 2012 Janaina Mourao-Miranda, Jane Maryam Rondina, Maria Joao Rosa (UCL): Machine learning approaches for clinical neuroimaging data
Fri, 13 Jul 2012 Vinayak Rao (UCL): Efficient MCMC for Continuous Time Discrete State Systems
Mon, 02 Jul 2012 Yuan (Alan) Qi (Purdue University): Bayesian learning with big data: virtual vector machines and Gaussian processes with sparse eigenval
Fri, 22 Jun 2012 Adam Sykulski (UCL): Statistical modelling and estimation of physical phenomena in ocean surface trajectories
Tue, 12 Jun 2012 Shivani Lamba, (Founder/CEO of Chechako) and Marshall Levine, (Wise Counsel for Chechako Ltd): Startup Pitch
Mon, 11 Jun 2012 Larry Wasserman (Carnegie Mellon University): Discussion
Fri, 25 May 2012 Gabi Teodoru (UCL): Spectral Learning of Latent Variable Models and its Interpretation as an Optimization Problem
Fri, 11 May 2012 Tom Furmston (UCL): Gradient-based algorithms for policy search
Fri, 27 Apr 2012 Mark Girolami (UCL): Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods