33 citations · 125 across the 19 of their papers we have counts for
20 papers
Beyond Quantification: Navigating Uncertainty in Professional AI Systems
Sylvie Delacroix, Diana Robinson, Umang Bhatt +12
The growing integration of large language models across professional domains transforms how experts make critical decisions in healthcare, education, and law. While significant res…
Continual Density Ratio Estimation in an Online Setting
Yu Chen, Song Liu, Tom Diethe +1
In online applications with streaming data, awareness of how far the training or test set has shifted away from the original dataset can be crucial to the performance of the model.…
Interpretable Anomaly Detection with Mondrian P{ó}lya Forests on Data Streams
Charlie Dickens, Eric Meissner, Pablo G. Moreno +1
Anomaly detection at scale is an extremely challenging problem of great practicality. When data is large and high-dimensional, it can be difficult to detect which observations do n…
Optimal Continual Learning has Perfect Memory and is NP-hard
Jeremias Knoblauch, Hisham Husain, Tom Diethe
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks. Designing CL algorithms that perform reliably and…
Semi-Discriminative Representation Loss for Online Continual Learning
Yu Chen, Tom Diethe, Peter Flach
The use of episodic memory in continual learning has demonstrated effectiveness for alleviating catastrophic forgetting. In recent studies, gradient-based approaches have been deve…
Similarity of Neural Networks with Gradients
Shuai Tang, Wesley J. Maddox, Charlie Dickens +2
A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights…
Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text
Oluwaseyi Feyisetan, Tom Diethe, Thomas Drake
Guaranteeing a certain level of user privacy in an arbitrary piece of text is a challenging issue. However, with this challenge comes the potential of unlocking access to vast data…
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations
Oluwaseyi Feyisetan, Borja Balle, Thomas Drake +1
Accurately learning from user data while providing quantifiable privacy guarantees provides an opportunity to build better ML models while maintaining user trust. This paper presen…
HyperStream: a Workflow Engine for Streaming Data
Tom Diethe, Meelis Kull, Niall Twomey +5
This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabili…
Distribution Calibration for Regression
Hao Song, Tom Diethe, Meelis Kull +1
We are concerned with obtaining well-calibrated output distributions from regression models. Such distributions allow us to quantify the uncertainty that the model has regarding th…
Automatic Discovery of Privacy-Utility Pareto Fronts
Brendan Avent, Javier Gonzalez, Tom Diethe +2
Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off pr…
Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
Yu Chen, Tom Diethe, Neil Lawrence
Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the…
Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
Oluwaseyi Feyisetan, Thomas Drake, Borja Balle +1
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for la…
Continual Learning in Practice
Tom Diethe, Tom Borchert, Eno Thereska +2
This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures th…
-IRT: A New Item Response Model and its Applications
Yu Chen, Telmo Silva Filho, Ricardo B. C. Prudêncio +2
Item Response Theory (IRT) aims to assess latent abilities of respondents based on the correctness of their answers in aptitude test items with different difficulty levels. In this…
Probabilistic Sensor Fusion for Ambient Assisted Living
Tom Diethe, Niall Twomey, Meelis Kull +2
There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home. Given a multiple-modality sensor platform…
The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data
Niall Twomey, Tom Diethe, Meelis Kull +8
This paper outlines the Sensor Platform for HEalthcare in Residential Environment (SPHERE) project and details the SPHERE challenge that will take place in conjunction with Europea…
A Note on the Kullback-Leibler Divergence for the von Mises-Fisher distribution
Tom Diethe
We present a derivation of the Kullback Leibler (KL)-Divergence (also known as Relative Entropy) for the von Mises Fisher (VMF) Distribution in -dimensions.
Data-dependent kernels in nearly-linear time
Guy Lever, Tom Diethe, John Shawe-Taylor
We propose a method to efficiently construct data-dependent kernels which can make use of large quantities of (unlabeled) data. Our construction makes an approximation in the stand…
Convex Multiview Fisher Discriminant Analysis
Tom Diethe, John Shawe-Taylor
Section 1.3 was incorrect, and 2.1 will be removed from further submissions. A rewritten version will be posted in the future.