Projecting Ising Model Parameters for Fast Mixing
This addresses computational bottlenecks in statistical physics and machine learning inference, though it is incremental as it builds on existing projection and sampling methods.
The authors tackled the problem of slow mixing in Ising models with strong interactions by projecting parameters onto a fast-mixing set, resulting in more accurate Gibbs sampling under time constraints.
Inference in general Ising models is difficult, due to high treewidth making tree-based algorithms intractable. Moreover, when interactions are strong, Gibbs sampling may take exponential time to converge to the stationary distribution. We present an algorithm to project Ising model parameters onto a parameter set that is guaranteed to be fast mixing, under several divergences. We find that Gibbs sampling using the projected parameters is more accurate than with the original parameters when interaction strengths are strong and when limited time is available for sampling.