I am happy to report that our paper on "Algorithms for the Communication of Samples" has been accepted to ICML 2022. This problem frequently crops up in neural compression but also in differential privacy. arxiv.org/abs/2110.12805
2
7
43
0
3
Among other contributions, we introduce a hybrid coding scheme which significantly reduces the computational cost of communicating a Gaussian sample (while also reducing the coding cost slightly).