A neural-network-parameterized differentiable particle filter trained with variational SMC outperforms baselines on Lorenz attractor tracking from high-dimensional and partial observations.
An overview of differentiable particle filters for data- adaptive sequential Bayesian inference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Variational Sequential Monte Carlo for High-Dimensional Observations
A neural-network-parameterized differentiable particle filter trained with variational SMC outperforms baselines on Lorenz attractor tracking from high-dimensional and partial observations.