ECE PhD Proposal Review: Berkan Kadioglu

PhD Proposal Review: Sample Complexity of Pairwise Ranking Regression

Berkan Kadioglu

Location: Zoom

Abstract: We consider a rank regression setting, in which a dataset of $N$ samples with features in $\mathbb{R}^d$ is ranked by an oracle via $M$ pairwise comparisons.
Specifically, there exists a latent total ordering of the samples; when presented with a pair of samples, a noisy oracle identifies the one ranked higher w.r.t. the underlying total ordering. A learner observes a dataset of such comparisons, and wishes to regress sample ranks from their features.
We show that to learn the model parameters with $\epsilon > 0$ accuracy, it suffices to conduct $M \in \Omega(dN\log^3 N/\epsilon^2)$ comparisons uniformly at random when $N$ is $\Omega(d/\epsilon^2)$.