MLLGSTOct 16, 2021

On Model Selection Consistency of Lasso for High-Dimensional Ising Models

arXiv:2110.08500v41 citations
Originality Highly original
AI Analysis

This provides rigorous theoretical guarantees for variable selection in high-dimensional statistical physics models, addressing a known bottleneck in sparse estimation.

The paper theoretically analyzes the model selection consistency of Lasso for high-dimensional Ising models, proving that Lasso without post-thresholding achieves consistency in the paramagnetic phase with sample complexity n=Ω(d^3 log p), matching prior conjectures and extending results to general tree-like graphs.

We theoretically analyze the model selection consistency of least absolute shrinkage and selection operator (Lasso), both with and without post-thresholding, for high-dimensional Ising models. For random regular (RR) graphs of size $p$ with regular node degree $d$ and uniform couplings $θ_0$, it is rigorously proved that Lasso \textit{without post-thresholding} is model selection consistent in the whole paramagnetic phase with the same order of sample complexity $n=Ω{(d^3\log{p})}$ as that of $\ell_1$-regularized logistic regression ($\ell_1$-LogR). This result is consistent with the conjecture in Meng, Obuchi, and Kabashima 2021 using the non-rigorous replica method from statistical physics and thus complements it with a rigorous proof. For general tree-like graphs, it is demonstrated that the same result as RR graphs can be obtained under mild assumptions of the dependency condition and incoherence condition. Moreover, we provide a rigorous proof of the model selection consistency of Lasso with post-thresholding for general tree-like graphs in the paramagnetic phase without further assumptions on the dependency and incoherence conditions. Experimental results agree well with our theoretical analysis.

Foundations

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

Your Notes