Search Mailing List Archives


Limit search to: Subject & Body Subject Author
Sort by: Reverse Sort
Limit to: All This Week Last Week This Month Last Month
Select Date Range     through    

[theory-seminar] "Towards instance-optimal compression for distributed mean estimation" – Ananda Theertha Suresh (Thu, 10-Mar @ 4:00pm)

Tavor Baharav tavorb at stanford.edu
Mon Mar 7 18:07:33 PST 2022


Towards instance-optimal compression for distributed mean estimationAnanda
Theertha Suresh – Research Scientist, Google Research

Thu, 10-Mar / 4:00pm / Zoom:
https://stanford.zoom.us/meeting/register/tJckfuCurzkvEtKKOBvDCrPv3McapgP6HygJ
(in person)

*Please join us for coffee and snacks at 3:30pm in the Grove outside
Packard (near Bytes' outdoor seating). The talk will be streamed on
Zoom: https://stanford.zoom.us/meeting/register/tJckfuCurzkvEtKKOBvDCrPv3McapgP6HygJ
<https://stanford.zoom.us/meeting/register/tJckfuCurzkvEtKKOBvDCrPv3McapgP6HygJ>*
Abstract

Distributed mean estimation is a commonly used subroutine in many
distributed learning and optimization algorithms. In several distributed
scenarios, communication cost is a bottleneck and quantization techniques
have been proposed to improve communication efficiency. However, existing
techniques often suffer a quantization error scaling with the range of data
points. We propose a new non-interactive correlated quantization protocol
whose error guarantee depends on the deviation of data points instead of
their absolute range. Furthermore, our algorithm and analysis does not make
any distribution assumptions or require any prior knowledge on the
concentration property of the data. We prove the optimality of our protocol
under mild assumptions and also show that applying it as a subroutine in
distributed optimization leads to better convergence rates.

Based on joint work with Jae Ro, Ziteng Sun, and Felix Yu.
Bio

Ananda Theertha Suresh is a research scientist at Google Research, New
York. He received his PhD from University of California San Diego, where he
was advised by Prof. Alon Orlitsky. His research focuses on theoretical and
algorithmic aspects of machine learning, information theory, differential
privacy, and statistics. He is a recipient of the 2017 Paul Baran Maroni
Young Scholar award and a co-recipient of best paper awards at NeurIPS
2015, ALT 2020, CCS 2021, and a best paper honorable mention award at ICML
2017.

*This talk is hosted by the ISL Colloquium
<https://isl.stanford.edu/talks/>. To receive talk announcements, subscribe
to the mailing list isl-colloq at lists.stanford.edu
<https://mailman.stanford.edu/mailman/listinfo/isl-colloq>.*
------------------------------

Mailing list: https://mailman.stanford.edu/mailman/listinfo/isl-colloq
This talk:
http://isl.stanford.edu/talks/talks/2022q1/ananda-theertha-suresh/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.stanford.edu/pipermail/theory-seminar/attachments/20220307/09c472c8/attachment.html>


More information about the theory-seminar mailing list