Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tom Diethe

Continual Density Ratio Estimation in an Online Setting


Mar 09, 2021
Yu Chen, Song Liu, Tom Diethe, Peter Flach


  Access Paper or Ask Questions

Interpretable Anomaly Detection with Mondrian P{贸}lya Forests on Data Streams


Aug 04, 2020
Charlie Dickens, Eric Meissner, Pablo G. Moreno, Tom Diethe


  Access Paper or Ask Questions

Bypassing Gradients Re-Projection with Episodic Memories in Online Continual Learning


Jun 19, 2020
Yu Chen, Tom Diethe, Peter Flach


  Access Paper or Ask Questions

Optimal Continual Learning has Perfect Memory and is NP-hard


Jun 09, 2020
Jeremias Knoblauch, Hisham Husain, Tom Diethe

* Accepted for publication at ICML (International Conference on Machine Learning) 2020; 13 pages, 8 Figures 

  Access Paper or Ask Questions

Similarity of Neural Networks with Gradients


Mar 25, 2020
Shuai Tang, Wesley J. Maddox, Charlie Dickens, Tom Diethe, Andreas Damianou


  Access Paper or Ask Questions

Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text


Oct 20, 2019
Oluwaseyi Feyisetan, Tom Diethe, Thomas Drake

* Accepted at ICDM 2019 

  Access Paper or Ask Questions

Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations


Oct 20, 2019
Oluwaseyi Feyisetan, Borja Balle, Thomas Drake, Tom Diethe

* Accepted at WSDM 2020 

  Access Paper or Ask Questions

HyperStream: a Workflow Engine for Streaming Data


Aug 07, 2019
Tom Diethe, Meelis Kull, Niall Twomey, Kacper Sokol, Hao Song, Miquel Perello-Nieto, Emma Tonkin, Peter Flach


  Access Paper or Ask Questions

Automatic Discovery of Privacy-Utility Pareto Fronts


May 26, 2019
Brendan Avent, Javier Gonzalez, Tom Diethe, Andrei Paleyes, Borja Balle


  Access Paper or Ask Questions

Distribution Calibration for Regression


May 15, 2019
Hao Song, Tom Diethe, Meelis Kull, Peter Flach

* ICML 2019, 10 pages 

  Access Paper or Ask Questions

Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients


Apr 24, 2019
Yu Chen, Tom Diethe, Neil Lawrence

* Continual Learning Workshop of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) 

  Access Paper or Ask Questions

Privacy-preserving Active Learning on Sensitive Data for User Intent Classification


Mar 26, 2019
Oluwaseyi Feyisetan, Thomas Drake, Borja Balle, Tom Diethe

* To appear at PAL: Privacy-Enhancing Artificial Intelligence and Language Technologies as part of the AAAI Spring Symposium Series (AAAI-SSS 2019) 

  Access Paper or Ask Questions

Continual Learning in Practice


Mar 18, 2019
Tom Diethe, Tom Borchert, Eno Thereska, Borja Balle, Neil Lawrence

* Presented at the NeurIPS 2018 workshop on Continual Learning https://sites.google.com/view/continual2018/home 

  Access Paper or Ask Questions

$尾^3$-IRT: A New Item Response Model and its Applications


Mar 13, 2019
Yu Chen, Telmo Silva Filho, Ricardo B. C. Prud锚ncio, Tom Diethe, Peter Flach

* AISTATS 2019 

  Access Paper or Ask Questions

Probabilistic Sensor Fusion for Ambient Assisted Living


Feb 04, 2017
Tom Diethe, Niall Twomey, Meelis Kull, Peter Flach, Ian Craddock

* Journal article. 19 pages; 7 figures 

  Access Paper or Ask Questions

A Note on the Kullback-Leibler Divergence for the von Mises-Fisher distribution


Feb 25, 2015
Tom Diethe

* 8 pages 1 figure 

  Access Paper or Ask Questions

Data-dependent kernels in nearly-linear time


Oct 20, 2011
Guy Lever, Tom Diethe, John Shawe-Taylor


  Access Paper or Ask Questions

Convex Multiview Fisher Discriminant Analysis


Oct 29, 2009
Tom Diethe, John Shawe-Taylor

* This paper has been withdrawn 

  Access Paper or Ask Questions