AI Paper Atlas

Research map / Time series / Causal and generative time series

Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes

Creighton Heaukulani, Mark van der Wilk

NeurIPS 2019 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use an additive white noise parameterization (ablation)Wishart process · Dow 30test loglikelihoodImproved
use an additive white noise parameterization (ablation)inverse Wishart process · Dow 30test loglikelihood: 164.09 ± 26.47 -> 164.49 ± 19.82Improved
use an additive white noise parameterization (ablation)inverse Wishart process · FXtest loglikelihood: 81.42 ± 4.12 -> 82.10 ± 3.72Improved
replace the full covariance model with a 10-factor model (ablation)Wishart process with additive white noise · Dow 30test loglikelihood: 165.98 ± 23.23 -> 165.39 ± 30.89Mixed
replace the full covariance model with a 10-factor model (ablation)Wishart process with additive white noise · FXtest loglikelihood: 82.69 ± 4.15 -> 81.12 ± 3.59Hurt
use a 10-factor rather than 30-factor model (ablation)Wishart process with additive white noise · S&P 500test loglikelihood: 1438.40 ± 130.14 -> 1423.31 ± 132.19Hurt
use an inverse Wishart process instead of a Wishart process10-factor model · FXtest loglikelihood: 81.12 ± 3.59 vs 77.76 ± 3.94Hurt
use an inverse Wishart process instead of a Wishart process30-factor model · S&P 500test loglikelihood: 1438.40 ± 130.14 vs 1047.73 ± 1436.16Hurt
use an inverse Wishart process instead of a Wishart processfull covariance model with additive white noise · FXtest loglikelihood: 82.69 ± 4.15 vs 82.10 ± 3.72Hurt
use a 10-factor inverse Wishart model rather than the ARCH baselineS&P 500 · S&P 500test loglikelihood: 1358.23 ± 355.12 vs 1275.27 ± 264.48Hurt
use a 10-factor Wishart model rather than the ARCH baselineS&P 500 · S&P 500test loglikelihood: 1358.23 ± 355.12 -> 1423.31 ± 132.19Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy