Adaptive mixture variational inference for spike-and-slab regression
Read the original on arXiv Statistics ML →The paper introduces an adaptive fitting procedure for mixtures of product distributions in Gaussian regression with a spike‑and‑slab prior, directly minimizing reverse Kullback‑Leibler divergence on inclusion indicators and active coefficients. This method jointly refines component parameters and weights as the mixture grows, avoiding extra divergence penalties on unused latent coefficients. Empirical results on 250 simulated datasets show that mixtures reduce errors in inclusion probabilities, grouped support probabilities, and coefficient covariance compared to multistart mean‑field approaches, and that direct joint refinement outperforms augmented or restricted refinement at fixed mixture size.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.