Past Papers

Here’s a list of the papers/videos that have previously been presented.

Date Presented By Paper Title
3rd December Pierre-Aurelien Gilliot Deep Boltzmann Machines - Ruslan Salakhutdinov
10th December Christophe Andrieu Multiscale Models for Image Classification and Physics with Deep Networks - Stéphane Mallat
17th December Anthony Lee Nonparametric regression using deep neural networks with ReLU activation function - Johannes Schmidt-Hieber
10th March Patrick Rubin-Delanchy Uniform convergence may be unable to explain generalization in deep learning - Vaishnavh Nagarajan
24th March Song Liu Neural Ordinary Differential Equations - Ricky T. Q. Chen
7th April Mark Beaumont Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation - Samuel Wiqvist
14th April Mauro Camara Escudero Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights - Daniel Soudry
21st April Mingxuan Yi Opening the black box of Deep Neural Networks via Information - Ravid Schwartz-Ziv
28th April Andi Wang Markov Chain Monte Carlo and Variational Inference: Bridging the Gap - Tim Salimans
5th May Sam Tickle Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series - Zahra Ebrahimzadeh
26th May Pierre Aurelien Gilliot Preventing Posterior Collapse with delta-VAEs - Ali Razavi
2nd June Christophe Andrieu MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference - Achille Thin
9nd June Anthony Lee From optimal transport to generative modeling: the VEGAN cookbook - Olivier Bousquet
25th June Song Liu Stein Variational Gradient Descent as Gradient Flow - Qiang Liu
30th June Mark Beaumont Mining gold from implicit models to improve likelihood-free inference - Johann Brehmer et al.
7th July Mauro Camara Escudero Auto-Encoding Variational Bayes - Diederik P. Kingma
14th July Mingxuan Yi Neural Processes - Marta Garnelo
28th July Mauro Camara Escudero Variational Inference with Normalizing Flows - Rezende & Mohamed
19th October Chang Zhang Learning in Implicit Generative Models - Mohamed et al
28th October Mauro Camara Escudero Adversarial Variational Bayes - Mescheder et al.
2nd November Song Liu Likelihood-free MCMC with Amortized Approximate Ratio Estimators - Hermans et al.
9nd November Pierre Aurelien Gilliot Learning Latent Subspaces in Variational Autoencoders - Klys et al.
16th November Mark Beaumont Analyzing Inverse Problems with Invertible Neural Networks - Ardizzone et al.
23rd November Mingxuan Yi Neural Tangent Kernel: Convergence and Generalization in Neural Networks - Jacot et al.
30th November Christophe Andrieu Estimation under invariant distributions - Yamato et al.
7th December Andi Wang Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning - Liu et al.
14th December Anthony Lee Stochastic Normalizing Flows - Wu et al.
3rd February Sam Tickle Deep learning of contagion dynamics on complex networks - Murphy et al.
10rd February Patrick Rubin-Delanchy Neural Word Embedding as Implicit Matrix Factorization - Levy et al.
24th February Sam Power How to Train Your Energy-Based Models - Song et al.
3rd March Henry Reeve NeuralFDR: Learning Discovery Thresholds from Hypothesis Features - Xia et al.
31st March Mark Beaumont Sequential Neural Posterior and Likelihood Approximation - Wiqvist et al.
7th April Anthony Lee A Shooting Formulation of Deep Learning - Vialard et al.
14th April Chang Zhang The Thermodynamic Variational Objective - Masrani et al.
21st April Song Liu Telescoping Density-Ratio Estimation - Rhodes et al.
29th April Mauro Camara Escudero Differentiable Particle Filtering via Entropy-Regularized Optimal Transport - Corenflos et al.
6th May Mingxuan Yi Generalized Sliced Wasserstein Distances - Kolouri et al.
12th May Andi Wang Hopfield Networks is All You Need - Ramsauer et al.
9th June Henry Reeve Test-Time Training with Self-Supervision for Generalization under Distribution Shifts - Sun et al.
23rd June Sam Power Deep Gaussian Processes - Damianou et al.
30rd June Daniel Lawson A Likelihood-Free Inference Framework for Population Genetic Data using Exchangeable Neural Networks - Chan et al.