sketch size
Feature-distributed sparse regression: a screen-and-clean approach
Jiyan Yang, Michael W. Mahoney, Michael Saunders, Yuekai Sun
Neural Information Processing Systems http://nips.cc/
Cost
We then provide an algorithm to efficiently sketch input data using such embeddings. The sketch size of the embedding used in the algorithm has a linear dependence on the number of sketching dimensions of the input.
Communication-efficientDistributedSGDwith Sketching
However,theoretical and empirical evidence both suggest that there is a maximum mini-batch size beyond which the number of iterations required toconvergestops decreasing, andgeneralization error begins toincrease [Maetal.,2017,Lietal., 2014, Golmant et al., 2018, Shallue et al., 2018, Keskar et al., 2016, Hoffer et al., 2017]. In this paper, we aim instead to decrease the communication cost per worker.
Private Federated Frequency Estimation: Adapting to the Hardness of the Instance Anonymous Author(s) Affiliation Address email
In what follows, we will focus on this regime and assume that d > n.
Private Federated Frequency Estimation: Adapting to the Hardness of the Instance
Work done during an internship at Google Research 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
A Additional Background
B, which is part of the linear least squares right-hand-side we can solve for.
