pith. sign in

Title resolution pending

For either ReLU/hinge/logistic loss with R(·) = ∥·∥1 regularization, m = Ω( ε−2klogk )is required

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Optimal Dimension-Free Sampling for Regularized Classification

cs.LG · 2026-05-22 · unverdicted · novelty 7.0

Establishes optimal dimension-free sampling complexities (k²/ε² for L2/k, k/ε² for L1/k, linear in k under bounded derivative) for regularized classification losses with matching lower bounds.

citing papers explorer

Showing 1 of 1 citing paper.

  • Optimal Dimension-Free Sampling for Regularized Classification cs.LG · 2026-05-22 · unverdicted · none · ref 12

    Establishes optimal dimension-free sampling complexities (k²/ε² for L2/k, k/ε² for L1/k, linear in k under bounded derivative) for regularized classification losses with matching lower bounds.