View on GitHub

Machine learning reading group

Imperial College London

Welcome to the homepage of the Imperial College London machine learning reading group. We meet Fridays at 13:00 in Huxley 658 online on MS Teams. Suggested papers can be found here.

To get the latest updates, sign up to the mailing list.

2020-2021

Date Presenter Paper Author(s) Notes
02/10/20        
09/10/20 Joe Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training Joe Stacey et al.  
16/10/20 Hans JDINAC: joint density-based non-parametric differential interaction network analysis and classification using high-dimensional sparse omics data Jiadong Ji et al.  
23/10/20 Kate A continual learning survey: Defying forgetting in classification tasks Matthias De Lange et al. An Introduction to Continual Learning
break        
06/11/20 Janith Meta-Learning Symmetries by Reparameterization Allan Zhou, Tom Knowles & Chelsea Finn  
13/11/20 Daniel GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability Daniel Lengyel et al.  
20/11/20 James Estimation of active pharmaceutical ingredients content using locally weighted partial least squares and statistical wavelength selection Sanghong Kim et al.  
27/11/20 Kai Training Agents using Upside-Down Reinforcement Learning Rupesh Kumar Srivastava et al.  
04/12/20 Jonathan      
11/12/20        
18/12/20        
25/12/20        

2019-2020

Date Presenter Paper Author(s) Notes
17/10/19 George Approximate Inference Turns Deep Networks into Gaussian Processes Mohammad Emtiyaz Khan et al.  
24/10/19 Onur Random Tessellation Forests Shufei Ge et al.  
31/10/19 Arinbjörn A Scalable Laplace Approximation for Neural Networks Hippolyt Ritter, Aleksandar Botev and David Barber  
07/11/19 Kate Reconciling modern machine learning practice and the bias-variance trade-off Mikhail Belkin, Daniel Hsu, Siyuan Ma and Soumik Mandal  
14/11/19 Alex An explicit link between Gaussian fields and Gaussian Markov random fields: The SPDE approach Finn Lindgren, Håvard Rue and Johan Lindström  
21/11/19 Sesh Lost Relatives of the Gumbel Trick Matej Balog et al.  
Break for workshop        
05/12/19 Daniel Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach Shuyue Hu, Chin-Wing Leung, Ho-fung Leung  
12/12/19 Tim A Model to Search for Synthesizable Molecules John Bradshaw et al.  
Break        
20/01/20 Jonathan The Kernel Interaction Trick: Fast Bayesian Discovery of Pairwise Interactions in High Dimensions Raj Agrawal et al.  
31/01/20 Emily Boosting Variational Inference Guo et al.  
07/02/20 George Determinantal point processes for machine learning (chapters 2 and 4) Alex Kulesza and Ben Taskar  
14/02/20 Kate On Bayesian new edge prediction and anomaly detection in computer networks Silvia Metelli and Nicholas Heard  
21/02/20        
28/02/20 Adriaan A scalable bootstrap for massive data Ariel Kleiner et al.  
06/03/20 Isak Super-Samples from Kernel Herding Yutian Chen, Max Welling and Alex Smola  
13/03/20 break      
20/03/20 Jonathan & Arinbjörn Benchmarking Bayesian Deep Learning with Diabetic Retinopathy Diagnosis Angelos Filos et al.  
27/03/20 Kate Integrated Clustering and Anomaly Detection (INCAD) for Streaming Data Sreelekha Guggilam et al.  
03/04/20 Emily Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders Nat Dilokthanakul et al.  
10/04/20 break      
17/04/20 Daniel Exploring Generalization in Deep Learning Neyshabur et al.  
24/04/20 Jonathan Unsupervised Data Augmentation for Consistency Training Qizhe Xie et al.  
01/05/20 Kai Discovering the Compositional Structure of Vector Representations with Role Learning Networks Paul Soulos et al. Slides
08/05/20 Bank holiday break      
15/05/20 Sesh Alleviating Label Switching with Optimal Transport Pierre Monteiller et al.  
22/05/20 Hans A latent Markov model for detecting patterns of criminal activity Francesco Bartolucci et al.  
29/05/20 Isak Introduction to Coresets: Accurate Coresets Ibrahim Jubran et al. Slides
05/06/20 Adriaan Weight Uncertainty in Neural Networks Charles Blundell et al.  
12/06/20 Kai The frontier of simulation-based inference Kyle Cranmer et al. Slides
19/06/20 Daniel Sharp Minima Can Generalize For Deep Nets Laurent Dinh et al.  
26/06/20 Janith A General Theory of Equivariant CNNs on Homogeneous Spaces Taco S. Cohen, Mario Geiger & Maurice Weiler  
03/07/20 Alex On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems Panayotis Mertikopoulos, Nadav Hallak, Ali Kavis & Volkan Cevher  
10/07/20 Kate Nonparametric Variational Auto-encoders for Hierarchical Representation Learning Prasoon Goyal et al.  
17/07/20 Harrison Bayesian Probabilistic Numerical Integration with Tree-Based Models Harrison Zhu et al.  
24/07/20 Zaf Deep active inference agents using Monte-Carlo methods Zafeirios Fountas et al.  
31/07/20 Kai Transforming task representations to allow deep learning models to perform novel tasks Andrew K. Lampinen & James L. McClelland Slides
07/08/20 Aravind Estimation and Inference of Heterogeneous Treatment Effects using Random Forests Stefan Wager & Susan Athey  
14/08/20 Summer break      
21/08/20 Summer break      
28/08/20 Adriaan Monte Carlo (importance) sampling within a benders decomposition algorithm for stochastic linear programs Gerd Infanger Whiteboard notes
04/09/20 Jonathan NGBoost: Natural Gradient Boosting for Probabilistic Prediction Tony Duan et al.  
11/09/20 Chatura Probabilistic Value-Deviation-Bounded Integer Codes for Approximate Communication Phillip Stanley-Marbell & Paul Hurley  
18/09/20        
25/09/20 Janith On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups Risi Kondor & Shubhendu Trivedi