发明公开
- 专利标题: Systems and Methods for Communication Efficient Distributed Mean Estimation
-
申请号: US18240799申请日: 2023-08-31
-
公开(公告)号: US20240098138A1公开(公告)日: 2024-03-21
- 发明人: Ananda Theertha Suresh , Sanjiv Kumar , Hugh Brendan McMahan , Xinnan Yu
- 申请人: Google LLC
- 申请人地址: US CA Mountain View
- 专利权人: Google LLC
- 当前专利权人: Google LLC
- 当前专利权人地址: US CA Mountain View
- 主分类号: H04L67/10
- IPC分类号: H04L67/10 ; G06F17/12 ; G06F17/16 ; G06F17/18 ; G06N7/01 ; G06N20/00 ; H03M7/30 ; H03M7/40
摘要:
The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).
信息查询