Home

Time & Location

Usually on Monday 1:30pm-3pm at the Gatsby Unit, UCL 3th floor seminar room. Please subscribe to our mailing list to receive announcements of upcoming talks. To enter the building, see here.

Events

Updated: 19-Dec-17

Date	Presenter	Topic	Reading	Supplement
18 Dec 2017	Michael	GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash	Heusel et al., 2017
27 Nov 2017	Dougal	Generalization in Deep Learning.	Kawaguchi et al., 2017
20 Nov 2017	Yisong Yue		Le et al., 2017
13 Nov 2017	Nicolas Keriven	Sketching for Large-Scale Learning of Mixture Models	Keriven et al., 2017
06 Nov 2017	Mikolaj Kasprzak	Stein’s method for functional approximations	Kasprzak et al., 2017
30 Oct 2017	Wenkai	Expectation Propagation in the large-data limit	Dehaene et al., 2017
23 Oct 2017	Heiko	Gradient Estimators for Implicit Models	Li et al., 2017
16 Oct 2017	Dougal	Optimally Learning Populations of Parameters	Tian et al., 2017
09 Oct 2017	Tamara	Bayesian learning of kernel embeddings	Flaxman et al., 2017
18 Sep 2017	Michael	Learning Infinite Layer Networks Without the Kernel Trick	Livni et al., 2017
24 Jul 2017	Heiko	Fast DPP sampling for Nystrom with application to kernel methods	Li et al., 2016
17 Jul 2017	Dougal	Fast and Provably Good Seedings for k-Means	Bachem et al., 2016
10 Jul 2017	Wittawat	A Linear time Kernel Goodness-of-Fit Test	Wittawat et al., 2017
03 Jul 2017	Maneesh	Deep Gaussian Processes for Regression using Approximate Expectation Propagation	Bui et al., 2016	whiteboard
19 Jun 2017	Michael	Local Group Invariant Representations via Orbit Embeddings	Raj et al., 2017
12 Jun 2017	Chris J. Maddison	Filtering Variational Objectives	Maddison et al., 2017
05 Jun 2017	Wenkai	Conditional Mean Embeddings for Model-Based Reinforcement	Lever et al., 2016
08 May 2017	Carlo Ciliberto	A Consistent Regularization Approach for Structured Prediction	Ciliberto et al., 2016
10 Apr 2017	Dougal	Wasserstein GAN Improved Training of Wasserstein GANs. Generalization and Equilibrium in Generative Adversarial Nets (GANs)	Arjovsky et al., 2017, Gulrajani et al., 2017, Arora et al., 2017
03 Apr 2017	Heiko	Variational Fourier features for Gaussian processes	Hensman et al., 2016
20 Mar 2017	Kenji Fukumizu
27 Feb 2017	Dougal	Equality of Opportunity in Supervised Learning. Inherent Trade-Offs in the Fair Determination of Risk Scores. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments.	Hardt et al., 2016, Kleinberg et al., 2017, Chouldechova 2016
20 Feb 2017	Wenkai	Showing versus doing: Teaching by demonstration Teaching with rewards and punishments: Reinforcement or communication?.	Ho et al., 2016, Ho et al., 2015
13 Feb 2017	Michael	Conditioning as disintegration	Chang & Pollard, 1995
06 Feb 2017	Manuel Gomez Rodriguez	RedQueen: An Online Algorithm for Smart Broadcasting in Social Networks
16 Jan 2017	Wittawat	Examples are not Enough, Learn to Criticize! Criticism for Interpretability	Kim et al., 2016	slides
19 Dec 2016	Maneesh	Composing graphical models with neural networks for structured representations and fast inference	Johnson et al., 2016
12 Dec 2016	Byron Boots	Incremental Variational Sparse Gaussian Process Regression	Cheng & Boots, 2016
28 Nov 2016	Dougal	Towards Principled Methods for Training Generative Adversarial Networks Mode Regularized Generative Adversarial Networks	Arjovsky, Bottou, 2017, Che et al., 2017
22 Nov 2016	Krzysztof Choromanski	A tale of P-matrices and TripleSpinners - the unreasonable effectiveness of structured models in nonlinear embeddings
14 Nov 2016	Shakir Mohamed, Balaji Lakshminarayanan, Dougal	Learning in Implicit Generative Models Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy	Mohamed & Lakshminarayanan, 2016, Sutherland et al., 2016
07 Nov 2016	Heiko	On Markov chain Monte Carlo methods for tall data	Bardenet et al., 2015
31 Oct 2016	Wittawat	Determinantal point processes for machine learning	Kulesza & Taskar, 2012	slides
24 Oct 2016	Lea	Variational Latent Gaussian Process for Recovering Single-Trial Dynamics from Population Spike Trains	Zhao & Park, 2016
17 Oct 2016	Elena	Gaussian Processes for Big Data	Hensman et al., 2013
10 Oct 2016	Kevin Li	Deep Generative Stochastic Networks Trainable by Backprop Generative Adversarial Networks. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets.	Bengio et al., 2014, Goodfellow et al., 2014, Chen et al., 2016	slides
26 Sep 2016	Joana	Bayesian model selection and information criteria
19 Sep 2016	Aapo	Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA	Hyvarinen & Morioka, 2016
05 Sep 2016	Wittawat	Gaussian Process Random Fields	Moore & Russell, 2015
25 Jul 2016	Arthur	Training Input-Output Recurrent Neural Networks through Spectral Methods	Sedghi & Anandkumar, 2016
18 Jul 2016	Gergo	Geometry of nonlinear least squares with applications to sloppy models and optimization	Transtrum et al., 2011
11 Jul 2016	Vincent	A Unifying Framework for Sparse Gaussian Process Approximation using Power Expectation Propagation	Bui et al., 2016
27 Jun 2016	Zoltan	General notions of statistical depth function	Zuo & Serfling, 2000	slides
20 Jun 2016	Heiko	Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics	Gutmann & Hyvarinen, 2012
13 Jun 2016	Alex	A Mathematical Motivation for Complex-Valued Convolutional Networks	Tygert et. al., 2016
06 Jun 2016	Fredrik	Understanding predictive information criteria for Bayesian models, Bayesian leave-one-out cross-validation approximations for Gaussian latent variable models	Gelman et. al., 2013, Vehtari et. al., 2016
23 May 2016	Wittawat	Bayesian Learning of Kernel Embeddings	Flaxman et. al., 2016
09 May 2016	Carlos	Estimation theory for stochastic gradient descent
25 Apr 2016	Kevin Li	A Probabilistic Theory of Deep Learning	Patel et. al., 2015
18 Apr 2016	Vincent	Generalized Additive Models: An Introduction with R	Wood 2006
11 Apr 2016	Maneesh	On Autoencoders and Score Matching for Energy Based Models	Swersky et. al., 2011
04 Apr 2016	Zoltan	Nonparametric Independence Testing for Small Sample Sizes	Ramdas & Wehbe, 2015	slides
21 Mar 2016	Heiko	Learning Structured Densities via Infinite Dimensional Exponential Families	Sun et al., 2015
29 Feb 2016	Wittawat	Bayesian Indirect Inference Using a Parametric Auxiliary Model	Drovandi et al., 2015	slides
15 Feb 2016	Song Liu	Estimating Density Ratio: Learning Changes of Patterns	Song Liu’s homepage	slides
08 Feb 2016	Vincent	MCMC for Variationally Sparse Gaussian Processes	Hensman et al., 2015
11 Jan 2016	Zoltan	Automatic differentiation	Baydin et al., 2015, Hoffmann 2015	slides
30 Nov 2015	Vincent	On Sparse variational methods and the Kullback-Leibler divergence between stochastic processes	Matthews et al., 2015
23 Nov 2015	Wittawat	On the High-dimensional Power of Linear-time Kernel Two-Sample Testing under Mean-difference Alternatives	Ramdas et al., 2014
16 Nov 2015	Heiko	NYTRO: When Subsampling Meets Early Stopping	Angles et al., 2015
09 Nov 2015	Arthur	What Regularized Auto-Encoders Learn from the Data Generating Distribution	Alain & Bengio, 2012
02 Nov 2015	Zoltan	Kernels Based Tests with Non-asymptotic Bootstrap Approaches for Two-sample Problems	Fromont et al., 2012	slides
26 Oct 2015	Mijung	Robust and Private Bayesian Inference	Dimitrakakis et al., 2014
12 Oct 2015	Wittawat	Estimating Mutual Information by Local Gaussian Approximation	Gao et al., 2015
05 Oct 2015	Kacper	Optimal Detection of Sparse Principal Components in High Dimension	Berthet and Rigollet, 2015
04 Aug 2015	Wittawat	Landmarking Manifolds with Gaussian Processes	Liang and Paisley, 2015	slides
20 Jul 2015	Tom	Safe Exploration for Optimization with Gaussian Processes	Sui et al., 2015
29 Jun 2015	Anna Choromanska	The Loss Surfaces of Multilayer Networks	homepage
17 Jun 2015	Arthur, Heiko	Stochastic Gradient Hamiltonian Monte Carlo	Chen et al., 2014
08 Jun 2015	Heiko	Hamiltonian ABC	Meeds et al., 2015	slides
18 May 2015	Wittawat	Deep Exponential Families	Ranganath et al., 2015	slides
11 May 2015	Maneesh	Section 7: Convex Relaxations and Upper Bounds	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008
27 Apr 2015	Kacper	Section 6: Variational Methods in Parameter Estimation	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008
20 Apr 2015	Wittawat	Section 5: Mean field methods	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008	slides
23 Mar 2015	Vincent	Section 4.3: Expectation propagation	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008	slides
12 Mar 2015	Zoltan	Proof of random Fourier features	Random features (Rahimi & Recht)	slides
23 Feb 2015	Vincent, Alessandro	Section 4.1, 4.2: Bethe-Kikuchi Graphical Models, ExpFam, Variational Inference	Wainwright & Jordan, 2008	slides
16 Feb 2015	Wittawat, Heiko	Chapter 3, 4.1: Sum-Product, Bethe Graphical Models, ExpFam, Variational Inference	Wainwright & Jordan, 2008	slides
09 Feb 2015	Maneesh	Chapter 3: Graphical Models as Exponential Families	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008	Maneesh’s lecture slides
26 Jan 2015	Tom, Maneesh	Chapter 1-3: Background on variational inference	Graphical Models, ExpFam, Variational Inference by Wainwright & Jordan, 2008	Tom’s slides
24 Nov 2014	Arthur, Zoltan, Tom	NIPS preview	Arthur on Ba & Caruana, NIPS 2014, Zoltan on Yang et. al., ICML 2014, Tom on Frigola et. al., NIPS 2014	Slides by Zoltan
17 Nov 2014	Mijung	Auto-Encoding Variational Bayes	Kingma & Welling, 2013
27 Oct 2014	Tom	A Spectral Algorithm for Learning Hidden Markov Models.	Hsu et. al., 2009
20 Oct 2014	Zoltan	Scalable Kernel Methods via Doubly Stochastic Gradients	Dai et. al., 2014	Zoltan’s slides
13 Oct 2014	Maneesh	spectral methods for latent time series models, SSID, spectral HMM	ML course slides
06 Oct 2014	Balaji	The Consensus Monte Carlo Algorithm	Scott et. al., 2013
21 Aug 2014	Vincent	Gaussian Processes for Underdetermined Source Separation	Liutkus, A. et. al., 2011
14 Aug 2014	Dino, Balaji, Heiko	Firefly Monte Carlo: Exact MCMC with Subsets of Data	Maclaurin & Adams, 2014
07 Aug 2014	Laurence	Bayesian Learning via Stochastic Gradient Langevin Dynamics	Welling & Teh, 2011 (ICML)
31 Jul 2014	Mijung	Distributed Stochastic Gradient MCMC	Ahn et al., 2014 (ICML)
16 May 2014	Zoltan	Fastfood (Fast kernel approximation methods)	Fastfood (Le et al., 2013)	Slides by Zoltan
09 May 2014	Dino, Arthur	Random features & Random kitchen sinks	Random features (Rahimi & Recht). Random kitchen sinks (Rahimi & Recht)	Random features by Arthur, Random kitchen sinks by Dino
04 Apr 2014	Balaji	Variational Learning of Inducing Variables in Sparse Gaussian Processes	Titsias 2009 (AISTATS)	slides
28 Mar 2014	Heiko	Bayesian Gaussian Process Latent Variable Model	Titsias & Lawrence 2010 (AISTATS)	slides