The PETL parameters are trained only on Task 1 (the'first-session') of a set of

Research efforts on learning implicit 3D shapes without 3D supervision have primarily resorted to binary occupancy[26,34]asthe representation, aiming tomatch reprojected 3D occupancytothe given binary masks. Current worksadopting signed distance functions (SDF) either require apretrained deep shape prior [27] or are limited to discretized representations [14] that do not scale up with resolution.

Moreover, distilling a synthetic version of sensitive data helps preserve privacy; a support set can beprovided toanend-user forthedownstream applications without disclosure ofdata.

Forlinear regression, we give a polynomial-time algorithm based on Celis-Dennis-Tapia optimization algorithms. For binary classification, we show how to efficiently implement itusing aproper agnostic learner (i.e., anEmpirical Risk Minimizer) for the class of interest.