Timezone: »
Poster
Distributed Mean Estimation with Limited Communication
Ananda Theertha Suresh · Felix Xinnan Yu · Sanjiv Kumar · Brendan McMahan
Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data with $n$ clients, a naive stochastic rounding approach yields a mean squared error (MSE) of $\Theta(d/n)$ and uses a constant number of bits per dimension per client. We then extend this naive algorithm in two ways: we show that applying a structured random rotation before quantization reduces the error to $\mathcal{O}((\log d)/n)$ and a better coding strategy further reduces the error to $\mathcal{O}(1/n)$. We also show that the latter coding strategy is optimal up to a constant in the minimax sense i.e., it achieves the best MSE for a given communication cost. We finally demonstrate the practicality of our algorithms by applying them to distributed Lloyd's algorithm for k-means and power iteration for PCA.
Author Information
Ananda Theertha Suresh (Google Research)
Felix Xinnan Yu (Google Research)
Sanjiv Kumar (Google Research, NY)
Brendan McMahan (Google)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Distributed Mean Estimation with Limited Communication »
Tue. Aug 8th 05:30 -- 05:48 AM Room C4.8
More from the Same Authors
-
2021 : Remember What You Want to Forget: Algorithms for Machine Unlearning »
Ayush Sekhari · Ayush Sekhari · Jayadev Acharya · Gautam Kamath · Ananda Theertha Suresh -
2021 : On the Renyi Differential Privacy of the Shuffle Model »
Antonious Girgis · Deepesh Data · Suhas Diggavi · Ananda Theertha Suresh · Peter Kairouz -
2021 : Learning with User-Level Privacy »
Daniel A Levy · Ziteng Sun · Kareem Amin · Satyen Kale · Alex Kulesza · Mehryar Mohri · Ananda Theertha Suresh -
2023 : Federated Heavy Hitter Recovery under Linear Sketching »
Adria Gascon · Peter Kairouz · Ziteng Sun · Ananda Suresh -
2023 : SpecTr: Fast Speculative Decoding via Optimal Transport »
Ziteng Sun · Ananda Suresh · Jae Ro · Ahmad Beirami · Himanshu Jain · Felix Xinnan Yu · Michael Riley · Sanjiv Kumar -
2023 : Brendan McMahan: Advances in Privacy and Federated Learning, with Applications to GBoard »
Brendan McMahan -
2023 Poster: Subset-Based Instance Optimality in Private Estimation »
Travis Dick · Alex Kulesza · Ziteng Sun · Ananda Suresh -
2023 Poster: Federated Heavy Hitter Recovery under Linear Sketching »
Adria Gascon · Peter Kairouz · Ziteng Sun · Ananda Suresh -
2023 Poster: Algorithms for bounding contribution for histogram estimation under user-level privacy »
Yuhan Liu · Ananda Suresh · Wennan Zhu · Peter Kairouz · Marco Gruteser -
2023 Poster: Efficient Training of Language Models using Few-Shot Learning »
Sashank Jakkam Reddi · Sobhan Miryoosefi · Stefani Karp · Shankar Krishnan · Satyen Kale · Seungyeon Kim · Sanjiv Kumar -
2022 Poster: In defense of dual-encoders for neural ranking »
Aditya Menon · Sadeep Jayasumana · Ankit Singh Rawat · Seungyeon Kim · Sashank Jakkam Reddi · Sanjiv Kumar -
2022 Spotlight: In defense of dual-encoders for neural ranking »
Aditya Menon · Sadeep Jayasumana · Ankit Singh Rawat · Seungyeon Kim · Sashank Jakkam Reddi · Sanjiv Kumar -
2022 Poster: The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning »
Wei-Ning Chen · Christopher Choquette Choo · Peter Kairouz · Ananda Suresh -
2022 Poster: Robust Training of Neural Networks Using Scale Invariant Architectures »
Zhiyuan Li · Srinadh Bhojanapalli · Manzil Zaheer · Sashank Jakkam Reddi · Sanjiv Kumar -
2022 Spotlight: The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning »
Wei-Ning Chen · Christopher Choquette Choo · Peter Kairouz · Ananda Suresh -
2022 Oral: Robust Training of Neural Networks Using Scale Invariant Architectures »
Zhiyuan Li · Srinadh Bhojanapalli · Manzil Zaheer · Sashank Jakkam Reddi · Sanjiv Kumar -
2022 Poster: Correlated Quantization for Distributed Mean Estimation and Optimization »
Ananda Suresh · Ziteng Sun · Jae Ro · Felix Xinnan Yu -
2022 Spotlight: Correlated Quantization for Distributed Mean Estimation and Optimization »
Ananda Suresh · Ziteng Sun · Jae Ro · Felix Xinnan Yu -
2021 Poster: Practical and Private (Deep) Learning Without Sampling or Shuffling »
Peter Kairouz · Brendan McMahan · Shuang Song · Om Dipakbhai Thakkar · Abhradeep Guha Thakurta · Zheng Xu -
2021 Spotlight: A Discriminative Technique for Multiple-Source Adaptation »
Corinna Cortes · Mehryar Mohri · Ananda Theertha Suresh · Ningshan Zhang -
2021 Spotlight: Practical and Private (Deep) Learning Without Sampling or Shuffling »
Peter Kairouz · Brendan McMahan · Shuang Song · Om Dipakbhai Thakkar · Abhradeep Guha Thakurta · Zheng Xu -
2021 Poster: A Discriminative Technique for Multiple-Source Adaptation »
Corinna Cortes · Mehryar Mohri · Ananda Theertha Suresh · Ningshan Zhang -
2021 Spotlight: Relative Deviation Margin Bounds »
Corinna Cortes · Mehryar Mohri · Ananda Theertha Suresh -
2021 Poster: A statistical perspective on distillation »
Aditya Menon · Ankit Singh Rawat · Sashank Jakkam Reddi · Seungyeon Kim · Sanjiv Kumar -
2021 Poster: Relative Deviation Margin Bounds »
Corinna Cortes · Mehryar Mohri · Ananda Theertha Suresh -
2021 Poster: Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces »
Ankit Singh Rawat · Aditya Menon · Wittawat Jitkrittum · Sadeep Jayasumana · Felix Xinnan Yu · Sashank Jakkam Reddi · Sanjiv Kumar -
2021 Spotlight: A statistical perspective on distillation »
Aditya Menon · Ankit Singh Rawat · Sashank Jakkam Reddi · Seungyeon Kim · Sanjiv Kumar -
2021 Spotlight: Disentangling Sampling and Labeling Bias for Learning in Large-output Spaces »
Ankit Singh Rawat · Aditya Menon · Wittawat Jitkrittum · Sadeep Jayasumana · Felix Xinnan Yu · Sashank Jakkam Reddi · Sanjiv Kumar -
2020 : Keynote Session 5: Advances and Open Problems in Federated Learning, by Brendan McMahan (Google) »
Brendan McMahan -
2020 Poster: Does label smoothing mitigate label noise? »
Michal Lukasik · Srinadh Bhojanapalli · Aditya Menon · Sanjiv Kumar -
2020 Poster: Low-Rank Bottleneck in Multi-head Attention Models »
Srinadh Bhojanapalli · Chulhee Yun · Ankit Singh Rawat · Sashank Jakkam Reddi · Sanjiv Kumar -
2020 Poster: Accelerating Large-Scale Inference with Anisotropic Vector Quantization »
Ruiqi Guo · Philip Sun · Erik Lindgren · Quan Geng · David Simcha · Felix Chern · Sanjiv Kumar -
2020 Poster: SCAFFOLD: Stochastic Controlled Averaging for Federated Learning »
Sai Praneeth Reddy Karimireddy · Satyen Kale · Mehryar Mohri · Sashank Jakkam Reddi · Sebastian Stich · Ananda Theertha Suresh -
2020 Poster: Federated Learning with Only Positive Labels »
Felix Xinnan Yu · Ankit Singh Rawat · Aditya Menon · Sanjiv Kumar -
2020 Poster: Is Local SGD Better than Minibatch SGD? »
Blake Woodworth · Kumar Kshitij Patel · Sebastian Stich · Zhen Dai · Brian Bullins · Brendan McMahan · Ohad Shamir · Nati Srebro -
2020 Poster: FedBoost: A Communication-Efficient Algorithm for Federated Learning »
Jenny Hamer · Mehryar Mohri · Ananda Theertha Suresh -
2019 : Structured matrices for efficient deep learning »
Sanjiv Kumar -
2019 Poster: Escaping Saddle Points with Adaptive Gradient Methods »
Matthew Staib · Sashank Jakkam Reddi · Satyen Kale · Sanjiv Kumar · Suvrit Sra -
2019 Poster: Agnostic Federated Learning »
Mehryar Mohri · Gary Sivek · Ananda Suresh -
2019 Poster: Semi-Cyclic Stochastic Gradient Descent »
Hubert Eichner · Tomer Koren · Brendan McMahan · Nati Srebro · Kunal Talwar -
2019 Oral: Semi-Cyclic Stochastic Gradient Descent »
Hubert Eichner · Tomer Koren · Brendan McMahan · Nati Srebro · Kunal Talwar -
2019 Oral: Agnostic Federated Learning »
Mehryar Mohri · Gary Sivek · Ananda Suresh -
2019 Oral: Escaping Saddle Points with Adaptive Gradient Methods »
Matthew Staib · Sashank Jakkam Reddi · Satyen Kale · Sanjiv Kumar · Suvrit Sra -
2019 Poster: Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling »
Shanshan Wu · Alexandros Dimakis · Sujay Sanghavi · Felix Xinnan Yu · Daniel Holtmann-Rice · Dmitry Storcheus · Afshin Rostamizadeh · Sanjiv Kumar -
2019 Oral: Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling »
Shanshan Wu · Alexandros Dimakis · Sujay Sanghavi · Felix Xinnan Yu · Daniel Holtmann-Rice · Dmitry Storcheus · Afshin Rostamizadeh · Sanjiv Kumar -
2018 Poster: Loss Decomposition for Fast Learning in Large Output Spaces »
En-Hsu Yen · Satyen Kale · Felix Xinnan Yu · Daniel Holtmann-Rice · Sanjiv Kumar · Pradeep Ravikumar -
2018 Oral: Loss Decomposition for Fast Learning in Large Output Spaces »
En-Hsu Yen · Satyen Kale · Felix Xinnan Yu · Daniel Holtmann-Rice · Sanjiv Kumar · Pradeep Ravikumar -
2017 Poster: Stochastic Generative Hashing »
Bo Dai · Ruiqi Guo · Sanjiv Kumar · Niao He · Le Song -
2017 Talk: Stochastic Generative Hashing »
Bo Dai · Ruiqi Guo · Sanjiv Kumar · Niao He · Le Song -
2017 Poster: A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions »
Jayadev Acharya · Hirakendu Das · Alon Orlitsky · Ananda Suresh -
2017 Poster: Maximum Selection and Ranking under Noisy Comparisons »
Moein Falahatgar · Alon Orlitsky · Venkatadheeraj Pichapati · Ananda Theertha Suresh -
2017 Talk: A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions »
Jayadev Acharya · Hirakendu Das · Alon Orlitsky · Ananda Suresh -
2017 Talk: Maximum Selection and Ranking under Noisy Comparisons »
Moein Falahatgar · Alon Orlitsky · Venkatadheeraj Pichapati · Ananda Theertha Suresh