1 code implementation • 14 Feb 2024 • Russell Tsuchida, Cheng Soon Ong, Dino Sejdinovic
Maximum likelihood and maximum a posteriori estimates in a reparameterisation of the final layer of the intensity function can be obtained by solving a (strongly) convex optimisation problem using projected gradient descent.
1 code implementation • 13 Feb 2024 • Dan MacKinlay, Russell Tsuchida, Dan Pagendam, Petra Kuhnert
The use of local messages in a graphical model structure ensures that the approach can efficiently handle complex dependence structures.
1 code implementation • 8 May 2023 • Abdelwahed Khamis, Russell Tsuchida, Mohamed Tarek, Vivien Rolland, Lars Petersson
This paper is about where and how optimal transport is used in machine learning with a focus on the question of scalable optimal transport.
1 code implementation • 11 Nov 2022 • Russell Tsuchida, Cheng Soon Ong
We consider a generalised setting where the canonical parameters of the exponential family are a nonlinear transformation of the latents.
no code implementations • 11 Oct 2022 • Changkun Ye, Nick Barnes, Lars Petersson, Russell Tsuchida
Zero-Shot Learning (ZSL) models aim to classify object classes that are not seen during the training process.
no code implementations • 24 Dec 2021 • Mengyan Zhang, Russell Tsuchida, Cheng Soon Ong
We consider the continuum-armed bandits problem, under a novel setting of recommending the best arms within a fixed budget under aggregated feedback.
no code implementations • ICLR 2022 • Russell Tsuchida, Suk Yee Yong, Mohammad Ali Armin, Lars Petersson, Cheng Soon Ong
We show that using a kernelised generalised linear model (kGLM) as an inner problem in a DDN yields a large class of commonly used DEQ architectures with a closed-form expression for the hidden layer parameters in terms of the kernel.
1 code implementation • 20 Feb 2020 • Russell Tsuchida, Tim Pearce, Chris van der Heide, Fred Roosta, Marcus Gallagher
Secondly, and more generally, we analyse the fixed-point dynamics of iterated kernels corresponding to a broad range of activation functions.
1 code implementation • 29 Nov 2019 • Russell Tsuchida, Fred Roosta, Marcus Gallagher
The model resulting from partially exchangeable priors is a GP, with an additional level of inference in the sense that the prior and posterior predictive distributions require marginalisation over hyperparameters.
1 code implementation • 15 May 2019 • Tim Pearce, Russell Tsuchida, Mohamed Zaki, Alexandra Brintrup, Andy Neely
A simple, flexible approach to creating expressive priors in Gaussian process (GP) models makes new kernels from a combination of basic kernels, e. g. summing a periodic and linear kernel can capture seasonal variation with a long term trend.
no code implementations • 19 Oct 2018 • Russell Tsuchida, Fred Roosta, Marcus Gallagher
In the analysis of machine learning models, it is often convenient to assume that the parameters are IID.
no code implementations • ICML 2018 • Russell Tsuchida, Farbod Roosta-Khorasani, Marcus Gallagher
An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network.