Private inference in quantized models
A typical setup in many machine learning scenarios involves a server that holds a model
and a user that possesses data, and the challenge is to perform inference while …
and a user that possesses data, and the challenge is to perform inference while …
Non-Binary Covering Codes for Low-Access Computations
Given a real dataset and a computation family, we wish to encode and store the dataset in a
distributed system so that any computation from the family can be performed by accessing a …
distributed system so that any computation from the family can be performed by accessing a …