1.8k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Turing InstituteGB178 papers
- University of OxfordGB114 papers
- University of WarwickGB102 papers
- Queen Mary University of LondonGB91 papers
- University of CambridgeGB89 papers
- University College LondonGB81 papers
- Imperial College LondonGB60 papers
- University of EdinburghGB54 papers
- University of ManchesterGB30 papers
- University of ExeterGB25 papers
- University of SouthamptonGB20 papers
- Centre National de la Recherche ScientifiqueFR19 papers
42 papers · 1 filter
Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
Damien Rouchouse, Antoine Gonon, Rémi Gribonval +1
A central challenge in understanding generalization is to obtain non-vacuous guarantees that go beyond worst-case complexity over data or weight space. Among existing approaches, P…
Learning via Surrogate PAC-Bayes
Antoine Picard-Weibel, Roman Moscoviz, Benjamin Guedj
PAC-Bayes learning is a comprehensive setting for (i) studying the generalisation ability of learning algorithms and (ii) deriving new learning algorithms by optimising a generalis…
Closed-form Filtering for Non-linear Systems
Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1
Sequential Bayesian Filtering aims to estimate the current state distribution of a Hidden Markov Model, given the past observations. The problem is well-known to be intractable for…
A note on regularised NTK dynamics with an application to PAC-Bayesian training
Eugenio Clerico, Benjamin Guedj
We establish explicit dynamics for neural networks whose training objective has a regularising term that constrains the parameters to remain close to their initial value. This keep…
Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisation
Maxime Haddouche, Benjamin Guedj
PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation boun…
A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them
Lars Henry Berge Olsen, Ingrid Kristine Glad, Martin Jullum +1
Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learnin…
A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
Ahmed Salih, Zahra Raisi-Estabragh, Ilaria Boscolo Galazzo +4
eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communica…
Characterizing the contribution of dependent features in XAI methods
Ahmed Salih, Ilaria Boscolo Galazzo, Zahra Raisi-Estabragh +3
Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpret…
Generalization Bounds with Data-dependent Fractal Dimensions
Benjamin Dupuis, George Deligiannidis, Umut Şimşekli
Providing generalization guarantees for modern neural networks has been a crucial task in statistical learning. Recently, several studies have attempted to analyze the generalizati…
Fully probabilistic deep models for forward and inverse problems in parametric PDEs
Arnaud Vadeboncoeur, Ömer Deniz Akyildiz, Ieva Kazlauskaite +2
We introduce a physics-driven deep latent variable model (PDDLVM) to learn simultaneously parameter-to-solution (forward) and solution-to-parameter (inverse) maps of parametric par…
Hierarchical Bayesian Modelling for Knowledge Transfer Across Engineering Fleets via Multitask Learning
L. A. Bull, D. Di Francesco, M. Dhada +5
A population-level analysis is proposed to address data sparsity when building predictive models for engineering infrastructure. Utilising an interpretable hierarchical Bayesian ap…
Measuring dissimilarity with diffeomorphism invariance
Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1
Measures of similarity (or dissimilarity) are a key ingredient to many machine learning algorithms. We introduce DID, a pairwise dissimilarity measure applicable to a wide range of…
Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
Alessandro Barp, Lancelot Da Costa, Guilherme França +4
In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making. Based on this identifica…
Learning dynamical systems from data: A simple cross-validation perspective, part III: Irregularly-Sampled Time Series
Jonghyeon Lee, Edward De Brouwer, Boumediene Hamzi +1
A simple and interpretable way to learn a dynamical system from data is to interpolate its vector-field with a kernel. In particular, this strategy is highly efficient (both in ter…
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms
Alexander Camuto, George Deligiannidis, Murat A. Erdogdu +3
Understanding generalization in deep learning has been one of the major challenges in statistical learning theory over the last decade. While recent work has illustrated that the d…
SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
Maud Lemercier, Cristopher Salvi, Thomas Cass +3
Making predictions and quantifying their uncertainty when the input data is sequential is a fundamental learning challenge, recently attracting increasing attention. We develop Sig…
Black-box density function estimation using recursive partitioning
Erik Bodin, Zhenwen Dai, Neill D. F. Campbell +1
We present a novel approach to Bayesian inference and general Bayesian computation that is defined through a sequential decision loop. Our method defines a recursive partitioning o…
Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks
Umut Şimşekli, Ozan Sener, George Deligiannidis +1
Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still…
Private Protocols for U-Statistics in the Local Model and Beyond
James Bell, Aurélien Bellet, Adrià Gascón +1
In this paper, we study the problem of computing -statistics of degree , i.e., quantities that come in the form of averages over pairs of data points, in the local model of d…
Ranking and synchronization from pairwise measurements via SVD
Alexandre d'Aspremont, Mihai Cucuringu, Hemant Tyagi
Given a measurement graph and an unknown signal , we investigate algorithms for recovering from pairwise measurements of the form ; $\…
The Extended Dawid-Skene Model: Fusing Information from Multiple Data Schemas
Michael P. J. Camilleri, Christopher K. I. Williams
While label fusion from multiple noisy annotations is a well understood concept in data wrangling (tackled for example by the Dawid-Skene (DS) model), we consider the extended prob…
A Review of Stochastic Block Models and Extensions for Graph Clustering
Clement Lee, Darren J Wilkinson
There have been rapid developments in model-based clustering of graphs, also known as block modelling, over the last ten years or so. We review different approaches and extensions…
Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels
Matthew Willetts, Stephen J Roberts, Christopher C Holmes
In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled data…
A Statistical Approach to Assessing Neural Network Robustness
Stefan Webb, Tom Rainforth, Yee Whye Teh +1
We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate th…