8 citations · 21 across the 5 of their papers we have counts for
5 papers
TCE: A Test-Based Approach to Measuring Calibration Error
Takuo Matsubara, Niek Tax, Richard Mudd +1
This paper proposes a new metric to measure the calibration error of probabilistic binary classifiers, called test-based calibration error (TCE). TCE incorporates a novel loss func…
Generalised Bayesian Inference for Discrete Intractable Likelihood
Takuo Matsubara, Jeremias Knoblauch, François-Xavier Briol +1
Discrete state spaces represent a major computational challenge to statistical inference, since the computation of normalisation constants requires summation over large or possibly…
Robust Generalised Bayesian Inference for Intractable Likelihoods
Takuo Matsubara, Jeremias Knoblauch, François-Xavier Briol +1
Generalised Bayesian inference updates prior beliefs using a loss function, rather than a likelihood, and can therefore be used to confer robustness against possible mis-specificat…
The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks
Takuo Matsubara, Chris J. Oates, François-Xavier Briol
Bayesian neural networks attempt to combine the strong predictive performance of neural networks with formal quantification of uncertainty associated with the predictive output in…
The global optimum of shallow neural network is attained by ridgelet transform
Sho Sonoda, Isao Ishikawa, Masahiro Ikeda +4
We prove that the global minimum of the backpropagation (BP) training problem of neural networks with an arbitrary nonlinear activation is given by the ridgelet transform. A series…