AIConfPaper
← Search

Marzia Polito

3 accepted papers

2022

DIVA: Dataset Derivative of a Learning Task

Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto
ICLR 2022poster

We present a method to compute the derivative of a learning task with respect to a dataset. A learning task is a function from a training set to the validation error, which can be represented by a trained deep neural network (DNN). The ``dataset derivative'' is a linear operator, computed around the…

Cited by 7Source ↗PDF ↗Scholar ↗
2021

LQF: Linear Quadratic Fine-Tuning

Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto
CVPR 2021poster

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are absent in deep neural networks (DNNs), typically trained by n…

Cited by 32PDF ↗Scholar ↗
2021

Mixed-Privacy Forgetting in Deep Networks

Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto
CVPR 2021poster

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining information after forgetting. Inspired by real-world…

Cited by 191PDF ↗Scholar ↗