Welcome to the homepage of the Imperial College London Computational Statistics and Machine Learning reading group. We meet Thursdays at 16:00 in Huxley 218 or online on MS Teams.

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

2024-2025

Date	Presenter	Paper	Author(s)	Notes
23/01/25	Hamidreza Kamkari	A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models	Hamidreza et al.
28/11/24	Jiajun He, Wenlin Chen, Mingtian Zhang	Training Neural Samplers with Reverse Diffusive KL Divergence	Jiajun He et al.
21/11/24	Shavindra Jayasekera	TBD
07/11/24	Michael Li	Multistage Learning in Reproducing Kernel Hilbert Space	Michael Li et al.
17/10/24	Yingzhen Li	Martingale posterior distributions	Edwin Fong et al.	slides

2023-2024

Date	Presenter	Paper	Author(s)	Notes
13/06/24	Jiayi Shen	Probabilistic Modeling for Knowledge Transfer
21/03/24	Mengyue Yang	Invariant Learning via Probability of Sufficient and Necessary Causes	Mengyue Yang et al.
07/03/24	Naoki Kiyohara	Beyond Attention: Unravelling the Potential of State Space Models for Sequential Data Processing		slides
29/02/24	Xiongjie Chen	Augmented Sliced Wasserstein Distances	Xiongjie Chen et al.
08/02/24	Aras Selvi	Extending the Scope of Wasserstein Machine Learning
01/02/24	Matthieu Meeus	Did the Neurons Read Your Book? Document-level Membership Inference for LLMs	Matthieu Meeus et al.
25/01/24	Mingxuan Yi	Divergence Minimizations: From Sample Space to Parameter Space
18/01/24	T. Anderson Keller	Traveling Waves in Brains and Machines
07/12/23	Fabrizio Russo	Shapley-PC: Constraint-based Causal Structure Learning with Shapley Values
30/11/23	Xavier Sumba-Toral	Connecting the dots: a journey of message passing in PGMs and MPNNs for approximate inference
23/11/23	Guoxuan Xia	Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models	Guoxuan Xia et al.
16/11/23	Tobias Schroeder	Energy Discrepancy: Fast Training of Energy-Based Models without MCMC	Tobias Schroeder et al.
09/11/23	Stathi Fotiadis	Image generation with shortest path diffusion	Ayan Das et al.
02/11/23	Tim Z. Xiao	What do we want from a generative model and how do we get it from a VAE?
26/10/23	Yingzhen Li	On the Identifiability of Markov Switching Models	Carles Balsells-Rodas et al.

2022-2023

Date	Presenter	Paper	Author(s)	Notes
13/07/23	Jin Xu	Deep Stochastic Processes via Functional Markov Transition Operators	Jin Xu et al.
01/06/23	Dinghuai Zhang	GFlowNets: Exploration for Structured Probabilistic Inference		slides
25/05/23	Jiaye Teng	Predictive Inference with Feature Conformal Prediction	Jiaye Teng et al.
11/05/23	Panagiotis Tigas	Differentiable Multi-Target Causal Bayesian Experimental Design	Yashas Annadani et al.
06/04/23	Fadhel Ayed	Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning	Francois Caron et al.
30/03/23	Zijing Ou	The modern arts of discrete EBMs training and inference		slides
23/03/23	Nihir Vedd, Zijing Ou, and Xing Liu	Casual discussion about the indication of GPT-4 to AI developments and research
09/03/23	Martin Jørgensen	Bézier Gaussian Processes for Tall and Wide Data	Martin Jørgensen et al.
02/03/23	Jose Folch	Neural Diffusion Process	Vincent Dutordoir et al.
23/02/23	Guoxuan Xia	Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data	Guoxuan Xia et al.
16/02/23	Max Weissenbacher	Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds	Bogdan Georgiev et al.
09/02/23	Cristopher Salvi	Recent developments in signature kernel methods
19/01/23	Vahid Balazadeh	Partial Identification of Treatment Effects with Implicit Generative Models	Vahid Balazadeh et al.
24/11/22	Harrison Zhu	Diffusion Models from an SDE Perspective
17/11/22	Wenlin Chen	Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction	Wenlin Chen et al.
10/11/22	Kevin H. Huang	Quantifying the Effects of Data Augmentation	Kevin H. Huang et al.
03/11/22	Anish Dhir	Combiner: Full Attention Transformer with Sparse Computation Cost	Hongyu Ren et al.
27/10/22	Tycho van der Ouderaa	Pathfinder: Parallel quasi-Newton variational inference	Lu Zhang et al.

2021-2022

Date	Presenter	Paper	Author(s)	Notes
23/06/22	Carles B. Rodas	Nonlinear ICA		slides
16/06/22	Tycho van der Ouderaa	Modern Laplace Approximations for Deep Learning
09/06/22	Hamzah Hashim and Alexander Pondaven	Convolutional Neural Processes for Inpainting Satellite Images
19/05/22	Wenlong Chen	Tutorial on (Stochastic Gradient) MCMC
12/05/22	Artem Artemev	Adaptive Cholesky Gaussian Processes	Simon Bartels et al.
05/05/22	Galen Wilkerson	Spontaneous Emergence of Computation in Network Cascades
28/04/22	Anish Dhir	Out of distribution generalisation using calibration

2020-2021

Date	Presenter	Paper	Author(s)	Notes
09/07/21	Yanni Papandreou	On Mahalanobis distance in functional settings	Berrendero et al.
02/07/21	Cris Salvi	On signature methods
25/06/21	Adam Howes	Small-area estimation with aggregated Gaussian processes	Adam Howes
18/06/21	Juliette Unwin	Multilevel Monte Carlo methods	Michael B. Giles
11/06/21	Michael Komodromos	Scalable Nonparametric Sampling from Multimodal Posteriors with the Posterior Bootstrap	Edwin Fong et al.
04/06/21	Harrison Zhu	Multi-resolution Spatial Regression for Aggregated Data with an Application to Crop Yield Prediction	Harrison Zhu et al.
28/05/21	Andrew Connell	Detecting changes in mean in the presence of time‐varying autocovariance	Euan T. McGonigle et al..
21/05/21
14/05/21	George Wynne	CovNet: Covariance Networks for Functional Data on Multidimensional Domains
07/05/21	Isak Falk
30/04/21	Swapnil Mishra
23/04/21	Tim Wolock
16/04/21	Thomas Mellan	Gaussian Process Nowcasting: Application to COVID-19 Mortality Reporting
09/04/21	Tresnia Berah	Validated Variational Inference via Practical Posterior Error Bounds
02/04/21	break
26/03/21	Harrison Zhu	Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
19/03/21	Xenia Miscouridou	Modelling sparsity, heterogeneity, reciprocity and community structure in temporal interaction data
26/02/21	Michael	Gaussian Processes for Survival Analysis	Tamara Fernández
19/02/21
12/02/21	Jonathan	Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases	Ryan Steed & Aylin Caliskan
05/02/21	Adriaan	Convolutional Gaussian Processes	Mark van der Wilk et al.
29/01/21	Kate	Optimal Transport for Domain Adaptation	Nicolas Courty et al.
break
04/12/20	Jonathan	Bayesian Deep Ensembles via the Neural Tangent Kernel	Bobby He, Balaji Lakshminarayanan and Yee Whye Teh
27/11/20	Kai	Training Agents using Upside-Down Reinforcement Learning	Rupesh Kumar Srivastava 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.
13/11/20	Daniel	GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability	Daniel Lengyel et al.
06/11/20	Janith	Meta-Learning Symmetries by Reparameterization	Allan Zhou, Tom Knowles & Chelsea Finn
break
23/10/20	Kate	A continual learning survey: Defying forgetting in classification tasks	Matthias De Lange et al.	An Introduction to Continual Learning
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.
09/10/20	Joe	Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training	Joe Stacey et al.
02/10/20

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