Search Results for author: Xuetong Wu

Found 10 papers, 0 papers with code

On the tightness of information-theoretic bounds on generalization error of learning algorithms

no code implementations26 Mar 2023 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

However, such a learning rate is typically considered to be ``slow", compared to a ``fast rate" of $O(\lambda/n)$ in many learning scenarios.

On the Value of Stochastic Side Information in Online Learning

no code implementations9 Mar 2023 Junzhang Jia, Xuetong Wu, Jingge Zhu, Jamie Evans

We study the effectiveness of stochastic side information in deterministic online learning scenarios.

An Information-Theoretic Analysis for Transfer Learning: Error Bounds and Applications

no code implementations12 Jul 2022 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

Specifically, we provide generalization error upper bounds for the empirical risk minimization (ERM) algorithm where data from both distributions are available in the training phase.

Domain Adaptation Transfer Learning

On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis

no code implementations10 May 2022 Xuetong Wu, Mingming Gong, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

We show that in causal learning, the excess risk depends on the size of the source sample at a rate of O(1/m) only if the labelling distribution between the source and target domains remains unchanged.

Unsupervised Domain Adaptation

Fast Rate Generalization Error Bounds: Variations on a Theme

no code implementations6 May 2022 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

However, such a learning rate is typically considered to be "slow", compared to a "fast rate" of O(1/n) in many learning scenarios.

A Bayesian Approach to (Online) Transfer Learning: Theory and Algorithms

no code implementations3 Sep 2021 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

Transfer learning is a machine learning paradigm where knowledge from one problem is utilized to solve a new but related problem.

Learning Theory Transfer Learning

Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge

no code implementations4 May 2021 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

On the one hand, it is conceivable that knowledge from one task could be useful for solving a related problem.

Transfer Learning

Transfer learning to enhance amenorrhea status prediction in cancer and fertility data with missing values

no code implementations1 Dec 2020 Xuetong Wu, Hadi Akbarzadeh Khorshidi, Uwe Aickelin, Zobaida Edib, Michelle Peate

Also, missing values are unavoidable in health and medical datasets and tackling the problem arising from the inadequate instances and missingness is not straightforward (Snell, et al. 2017, Sterne, et al. 2009).

BIG-bench Machine Learning regression +1

Imputation techniques on missing values in breast cancer treatment and fertility data

no code implementations16 Nov 2020 Xuetong Wu, Hadi Akbarzadeh Khorshidi, Uwe Aickelin, Zobaida Edib, Michelle Peate

Clinical decision support using data mining techniques offers more intelligent way to reduce the decision error in the last few years.

Imputation

Information-theoretic analysis for transfer learning

no code implementations18 May 2020 Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu

Specifically, we provide generalization error upper bounds for general transfer learning algorithms and extend the results to a specific empirical risk minimization (ERM) algorithm where data from both distributions are available in the training phase.

Domain Adaptation Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.