2025
On Traceability in $\ell_p$ Stochastic Convex Optimization
NeurIPS 2025spotlight
In this paper, we investigate the necessity of traceability for accurate learning in stochastic convex optimization (SCO) under $\ell_p$ geometries. Informally, we say a learning algorithm is \emph{$m$-traceable} if, by analyzing its output, it is possible to identify at least $m$ of its training sa…