Recursive Nested Filtering for Efficient Amortized Bayesian Experimental Design
This provides a practical and provably consistent approach for researchers and practitioners needing efficient experimental design in sequential Bayesian frameworks.
The paper tackles the problem of amortized sequential Bayesian experimental design in non-exchangeable settings by introducing the Inside-Out Nested Particle Filter (IO-NPF), which achieves O(T^2) computational complexity and demonstrates improved efficiency over existing methods.
This paper introduces the Inside-Out Nested Particle Filter (IO-NPF), a novel, fully recursive, algorithm for amortized sequential Bayesian experimental design in the non-exchangeable setting. We frame policy optimization as maximum likelihood estimation in a non-Markovian state-space model, achieving (at most) $\mathcal{O}(T^2)$ computational complexity in the number of experiments. We provide theoretical convergence guarantees and introduce a backward sampling algorithm to reduce trajectory degeneracy. IO-NPF offers a practical, extensible, and provably consistent approach to sequential Bayesian experimental design, demonstrating improved efficiency over existing methods.