On Traceability in ${\ell }_p$ Stochastic Convex Optimization

Sasha Voitovych, Mahdi Haghifam, Idan Attias +3

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 a…