A FISTA-based method with a custom PAVA computes perspective-relaxation dual bounds for k-sparse GLMs in O(p log p) per prox evaluation, enabling larger optimality certificates.
Proof of Theorem 3.6 Theorem 3.6.For anyβ∈R p, Algorithm 2 computes the exact value ofg(β), defined in(7), inO(p+plogk)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scalable First-order Method for Certifying Optimal k-Sparse GLMs
A FISTA-based method with a custom PAVA computes perspective-relaxation dual bounds for k-sparse GLMs in O(p log p) per prox evaluation, enabling larger optimality certificates.