OCDSLGJul 5

Fast, Parallel, Query-Efficient Binary Classification

arXiv:2607.040627.9
Predicted impact top 31% in OC · last 90 daysOriginality Incremental advance
AI Analysis

For researchers in large-scale machine learning, this work offers faster and more parallelizable algorithms for a fundamental classification problem, though the improvements are incremental over recent deterministic results.

This paper presents two randomized algorithms for binary classification that compute a separating hyperplane with near-optimal matrix-vector query complexity, achieving improved sequential runtime and parallel depth compared to prior deterministic methods.

We study the fundamental classification problem of computing a separating hyperplane for a binary-labeled dataset of size $n$ with normalized $d$-dimensional features. Letting $Φ\in \mathbb{R}^{n \times d}$ denote the feature matrix and $γ$ the margin of the maximum-margin separating hyperplane, we present a randomized algorithm that solves this problem in $\tilde{O}(γ^{-2/3}\, \operatorname{nnz}(Φ) + γ^{-2(ω+1)/3})$-sequential running time (work), $\tilde{O}(γ^{-2/3})$-parallel (computational) depth, and accesses $Φ$ only through $\tilde{O}(γ^{-2/3})$-matrix-vector queries (matvecs). We also present a second, faster randomized algorithm with a $\tilde{O}(γ^{-2/3}\, \operatorname{nnz}(Φ) + γ^{-2})$-sequential running time that uses $\tilde{O}(γ^{-2/3})$-matvecs to $Φ$, but achieves only $\tilde{O}(γ^{-4/3})$-parallel depth. Both algorithms match the near-optimal deterministic matvec complexity recently established by Kornowski and Shamir [2025], Karmarkar et al. [2026] and achieve improved sequential runtime and parallel depth, albeit at the expense of using randomness.

Foundations

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

Your Notes