Revisiting semi-supervised training objectives for differentiable particle filters
This work addresses the challenge of limited labeled data for training differentiable particle filters, which is an incremental improvement in the field.
The paper tackled the problem of training differentiable particle filters with scarce labeled data by comparing two semi-supervised training objectives, achieving results in two simulated environments.
Differentiable particle filters combine the flexibility of neural networks with the probabilistic nature of sequential Monte Carlo methods. However, traditional approaches rely on the availability of labelled data, i.e., the ground truth latent state information, which is often difficult to obtain in real-world applications. This paper compares the effectiveness of two semi-supervised training objectives for differentiable particle filters. We present results in two simulated environments where labelled data are scarce.