shihching.fu@postgrad.curtin.edu.au
Supervisors:
Dr Arash Bahramian, Dr Aloke Phatak,
Dr James Miller-Jones, Dr Suman Rakshit
Treat the varying brightness of a source as a stochastic process
Magnitude
Magnitude
Magnitude
Time (days)
Orbital Phase
Time (MJD)
Y is a vector of n Gaussian distributed random variables.
where \(\boldsymbol\mu = (\mu_1, \dots, \mu_n)\) and \(\boldsymbol{\Sigma}\) is a \(n \times n \) covariance matrix.
Extend multivariate Gaussian to 'infinite' dimensions.
where \(\mu = \mu(t)\) and \( K_{ij} = \kappa(t_i, t_j; \boldsymbol{\theta}) \), for \( i,j = 1, 2, \dots \)
Rather than specify a fixed covariance matrix with fixed dimensions, compute covariances using the kernel function.
Squared Exponential
Matern 3/2
Periodic
$$\kappa(\tau; \sigma, \ell) = \sigma^2 \exp\left\{ -\frac{1}{2}\left( \frac{\tau}{\ell}\right)^2\right\}$$
$$\kappa(\tau; \sigma, \ell) = \sigma^2 \left( 1 + \sqrt{3}\frac{\tau}{\ell}\right) \exp\left\{ - \sqrt{3} \frac{\tau}{\ell}\right\}$$
$$\kappa(\tau; \sigma, \ell, T) = \sigma^2 \exp\left\{ -\frac{2}{\ell^2} \sin^2\left( \pi \frac{\tau}{T}\right)\right\}$$
Squared Exponential
Matern 3/2
Periodic
\(Y_i \sim \mathcal{N}\left(f_i, \hat{e_i}^2\right)\)
\(\boldsymbol{f} \sim \mathcal{GP}\left(\boldsymbol{0}, \boldsymbol{\Sigma}_{n \times n}\right)\)
Hyperparameters
Respone
GP prior
Credit: Tetarenko et al. (2017)
Black hole X-ray binary
V404 Cygni
Credit: NRAO/AUI/NSF
Credit: ALMA (ESO/NAOH/NRAO)
\((n_1 + n_2) \times 1\)
\((n_1 + n_2) \times (n_1 + n_2)\)
Cross-covariance
\(\boldsymbol{K}_{\boldsymbol{f},\boldsymbol{f}}\)
\(\boldsymbol{K}_{\boldsymbol{f},\boldsymbol{f}}\)
?
?
Fit each band as a linear combination of two latent GPs,
where \(d = 1,2\) output bands and \(q = 1,2\) latent processes
Alternatively,
Co-regionalisation Matrices
Kronecker product
Cross-covariance between channels is the same shape as the auto-covariance.
Cannot model any lag between channels.
(Figure adapted from Parra & Tobar 2017)
Closed-form covariance functions after inverse Fourier transform.
For \(Q\) spectral components, the covariance between bands \(i\) and \(j\) at lag \(\tau = t - t'\) is
For a single component, \(Q = 1\):
"Squared Exponential envelope"
Periodic oscillation
The cross-band parameters are built from the per-band weight \(w_i\), spectral mean \(\mu_i\), spectral variance \(\Sigma_i\), delay \(\theta_i\) and phase \(\phi_i\):
Width of cross-covariance envelope
Delay between bands
Phase offset
Oscillation frequency of cross-covariance
Strength of coupling between bands
Amplitude of cross-covariance
Data Model
Process Model
length-scale in time
variance contribution of component \(q\)
split from total variance of band \(i\)
Identifiability constraints
\(s_{q,i}\) is the share of a band \(i\)’s signal variance carried by component \(q\).
\(\varsigma_i\) is the total standard deviation of the signal captured in band \(i\) .
\(\ell_{q,i}\) is the length scale of Component \(q\) band \(i\) .
| Band 1 | Band 2 | |
|---|---|---|
| Component 1 | 0.0076 | 0.0002 |
| Component 2 | 0.0002 | 0.010 |
\(\vartheta_{q}\) is time delay between Bands 1 and 2.