Efficient Learning of Deep State Space Models via Importance Smoothing 事件

Efficient Learning of Deep State Space Models via Importance Smoothing arXiv:2605.21108v2 Announce Type: replace-cross Abstract: Latent state space systems are ubiquitous in statistical modelling, arising naturally when time series are observed through noisy measurements. However, training deep state space models (DSSMs) at scale remains difficult. Two largely distinct strategies have emerged for training DSSMs. The first, auto-encoding DSSMs, trains generative models by optimising a variationa