AIJan 31, 2018

Lifted Filtering via Exchangeable Decomposition

arXiv:1801.10495v2
Originality Incremental advance
AI Analysis

This work addresses inference complexity in probabilistic systems where entity identities don't matter, though it appears incremental as it combines existing concepts like multisets, lifting, and Rao-Blackwellization.

The paper tackles the problem of exact recursive Bayesian filtering in systems with exchangeable random variables by introducing a model based on lifted multiset states, achieving exponential reduction in complexity when exchangeability holds.

We present a model for exact recursive Bayesian filtering based on lifted multiset states. Combining multisets with lifting makes it possible to simultaneously exploit multiple strategies for reducing inference complexity when compared to list-based grounded state representations. The core idea is to borrow the concept of Maximally Parallel Multiset Rewriting Systems and to enhance it by concepts from Rao-Blackwellization and Lifted Inference, giving a representation of state distributions that enables efficient inference. In worlds where the random variables that define the system state are exchangeable -- where the identity of entities does not matter -- it automatically uses a representation that abstracts from ordering (achieving an exponential reduction in complexity) -- and it automatically adapts when observations or system dynamics destroy exchangeability by breaking symmetry.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes