← Authors

Brendan Mcmahan

18 papers · 2007–2023 · 4 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (16) πŸ—ΊοΈ Taxonomy Completionist (12) 🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌟 Keyword Trendsetter Combo (6) πŸ† Keyword Champion πŸ’Ž Century Club (18) πŸš€ Conference Pioneer πŸ“ˆ Trend Setter ❓ The Questioner πŸ”₯ Unstoppable (5) πŸ—ƒοΈ Keyword Collector (84)

Conferences

NIPS (9) AISTATS (4) ICML (4) ACL (1)

Top co-authors

Peter Kairouz (4) Om Thakkar (3) Galen Andrew (2) Matthew Streeter (2) Nathan Srebro (2) Zheng Xu (2) Wennan Zhu (1) Yanxiang Zhang (1) Hubert Eichner (1) Abhradeep Thakurta (1)

Research topics

Privacy (1)

Keywords

federated learning (8) differential privacy (6) stochastic gradient descent (4) convex optimization (3) distributed learning (3) regret bound (3) distributed optimization (2) online learning (2) unconstrained optimization (2) online convex optimization (2) communication efficiency (2) sample complexity (1) randomized rounding (1) supervised learning (1) game theory (1) active learning (1) gaussian process (1) regret minimization (1) l1 regularization (1) privacy-preserving learning (1)

Papers

Federated Learning of Gboard Language Models with Differential Privacy ACL 2023
Practical and Private (Deep) Learning Without Sampling or Shuffling ICML 2021
Differentially Private Learning with Adaptive Clipping NIPS 2021
Federated Heavy Hitters Discovery with Differential Privacy AISTATS 2020
Privacy Amplification via Random Check-Ins NIPS 2020
Is Local SGD Better than Minibatch SGD? ICML 2020
Semi-Cyclic Stochastic Gradient Descent ICML 2019
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization NIPS 2018
cpSGD: Communication-efficient and differentially-private distributed SGD NIPS 2018
Communication-Efficient Learning of Deep Networks from Decentralized Data AISTATS 2017
Delay-Tolerant Algorithms for Asynchronous Distributed Online Learning NIPS 2014
Minimax Optimal Algorithms for Unconstrained Linear Optimization NIPS 2013
Large-Scale Learning with Less RAM via Randomization ICML 2013
Estimation, Optimization, and Parallelism when Data is Sparse NIPS 2013
No-Regret Algorithms for Unconstrained Online Convex Optimization NIPS 2012
Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization AISTATS 2011
Discussion of β€œContextual Bandit Algorithms with Supervised Learning Guarantees” AISTATS 2011
Selecting Observations against Adversarial Objectives NIPS 2007