2 papers
cs.LG2025
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
Ali Younis, Erik B. Sudderth
For challenging state estimation problems arising in domains like vision and robotics, particle-based representations attractively enable temporal reasoning about multiple posterio…
cs.LG2024
Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
Ali Younis, Erik Sudderth
Particle filters flexibly represent multiple posterior modes nonparametrically, via a collection of weighted samples, but have classically been applied to tracking problems with kn…