Timezone: »
Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline. Hyperparameter optimization is even more challenging in federated learning, where models are learned over a distributed network of heterogeneous devices; here, the need to keep data on device and perform local training makes it difficult to efficiently train and evaluate configurations. In this work, we investigate the problem of federated hyperparameter tuning. We first identify key challenges and show how standard approaches may be adapted to form baselines for the federated setting. Then, by making a novel connection to the neural architecture search technique of weight-sharing, we introduce a new method, FedEx, to accelerate federated hyperparameter tuning that is applicable to widely-used federated optimization methods such as FedAvg and recent variants. Theoretically, we show that a FedEx variant correctly tunes the on-device learning rate in the setting of online convex optimization across devices. Empirically, we show that FedEx can outperform natural baselines for federated hyperparameter tuning by several percentage points on the Shakespeare, FEMNIST, and CIFAR-10 benchmarks—obtaining higher accuracy using the same training budget.
Author Information
Mikhail Khodak (CMU)
Renbo Tu (CMU, Carnegie Mellon University)
Tian Li (CMU)
Liam Li (Carnegie Mellon University)
Maria-Florina Balcan (Carnegie Mellon University)
Virginia Smith (Carnegie Mellon University)
Ameet Talwalkar (CMU)
More from the Same Authors
-
2021 Spotlight: Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond »
Maria-Florina Balcan · Siddharth Prasad · Tuomas Sandholm · Ellen Vitercik -
2021 : Simulated User Studies for Explanation Evaluation »
Valerie Chen · Gregory Plumb · Nicholay Topin · Ameet S Talwalkar -
2021 : Bayesian Persuasion for Algorithmic Recourse »
Keegan Harris · Valerie Chen · Joon Sik Kim · Ameet Talwalkar · Hoda Heidari · Steven Wu -
2021 : Bayesian Persuasion for Algorithmic Recourse »
Keegan Harris · Valerie Chen · Joon Kim · Ameet S Talwalkar · Hoda Heidari · Steven Wu -
2021 : Bayesian Persuasion for Algorithmic Recourse »
Keegan Harris · Valerie Chen · Joon Kim · Ameet S Talwalkar · Hoda Heidari · Steven Wu -
2022 : Differentially Private Adaptive Optimization with Delayed Preconditioners »
Tian Li · Manzil Zaheer · Ken Liu · Sashank Reddi · H. Brendan McMahan · Virginia Smith -
2022 : Differentially Private Adaptive Optimization with Delayed Preconditioners »
Tian Li · Manzil Zaheer · Ken Liu · Sashank Reddi · H. Brendan McMahan · Virginia Smith -
2022 : Motley: Benchmarking Heterogeneity and Personalization in Federated Learning »
Shanshan Wu · Tian Li · Zachary Charles · Yu Xiao · Ken Liu · Zheng Xu · Virginia Smith -
2022 : AutoML for Climate Change: A Call to Action »
Renbo Tu · Nicholas Roberts · Vishak Prasad C · Sibasis Nayak · Paarth Jain · Frederic Sala · Ganesh Ramakrishnan · Ameet Talwalkar · Willie Neiswanger · Colin White -
2022 : Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts »
Amrith Setlur · Don Dennis · Benjamin Eysenbach · Aditi Raghunathan · Chelsea Finn · Virginia Smith · Sergey Levine -
2023 Poster: Progressive Knowledge Distillation: Constructing Ensembles for Efficient Inference »
Don Dennis · Abhishek Shetty · Anish Prasad Sevekari · Kazuhito Koishida · Virginia Smith -
2023 Poster: Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift »
Saurabh Garg · Amrith Setlur · Zachary Lipton · Sivaraman Balakrishnan · Virginia Smith · Aditi Raghunathan -
2023 Poster: Meta-Learning Adversarial Bandit Algorithms »
Misha Khodak · Ilya Osadchiy · Keegan Harris · Maria-Florina Balcan · Kfir Y. Levy · Ron Meir · Steven Wu -
2023 Poster: Learning with Explanation Constraints »
Rattana Pukdee · Dylan Sam · J. Zico Kolter · Maria-Florina Balcan · Pradeep Ravikumar -
2023 Poster: Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies »
Oscar Li · James Harrison · Jascha Sohl-Dickstein · Virginia Smith · Luke Metz -
2023 Poster: Bicriteria Multidimensional Mechanism Design with Side Information »
Siddharth Prasad · Maria-Florina Balcan · Tuomas Sandholm -
2023 Poster: New Bounds for Hyperparameter Tuning of Regression Problems Across Instances »
Maria-Florina Balcan · Anh Nguyen · Dravyansh Sharma -
2023 Poster: Reliable learning in challenging environments »
Maria-Florina Balcan · Steve Hanneke · Rattana Pukdee · Dravyansh Sharma -
2023 : Evaluating Large-Scale Learning Systems, Virginia Smith »
Virginia Smith -
2022 Competition: AutoML Decathlon: Diverse Tasks, Modern Methods, and Efficiency at Scale »
Samuel Guo · Cong Xu · Nicholas Roberts · Misha Khodak · Junhong Shen · Evan Sparks · Ameet Talwalkar · Yuriy Nevmyvaka · Frederic Sala · Anderson Schneider -
2022 : Panel »
Virginia Smith · Michele Covell · Daniel Severo · Christopher Schroers -
2022 : Poster Session 1 »
Andrew Lowy · Thomas Bonnier · Yiling Xie · Guy Kornowski · Simon Schug · Seungyub Han · Nicolas Loizou · xinwei zhang · Laurent Condat · Tabea E. Röber · Si Yi Meng · Marco Mondelli · Runlong Zhou · Eshaan Nichani · Adrian Goldwaser · Rudrajit Das · Kayhan Behdin · Atish Agarwala · Mukul Gagrani · Gary Cheng · Tian Li · Haoran Sun · Hossein Taheri · Allen Liu · Siqi Zhang · Dmitrii Avdiukhin · Bradley Brown · Miaolan Xie · Junhyung Lyle Kim · Sharan Vaswani · Xinmeng Huang · Ganesh Ramachandra Kini · Angela Yuan · Weiqiang Zheng · Jiajin Li -
2022 : Contributed Talks 1 »
Courtney Paquette · Tian Li · Guy Kornowski -
2022 : To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning »
Yae Jee Cho · Divyansh Jhunjhunwala · Tian Li · Virginia Smith · Gauri Joshi -
2022 Poster: Use-Case-Grounded Simulations for Explanation Evaluation »
Valerie Chen · Nari Johnson · Nicholay Topin · Gregory Plumb · Ameet Talwalkar -
2022 Poster: Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts »
Maria-Florina Balcan · Siddharth Prasad · Tuomas Sandholm · Ellen Vitercik -
2022 Poster: On Privacy and Personalization in Cross-Silo Federated Learning »
Ken Liu · Shengyuan Hu · Steven Wu · Virginia Smith -
2022 Poster: Provably tuning the ElasticNet across instances »
Maria-Florina Balcan · Misha Khodak · Dravyansh Sharma · Ameet Talwalkar -
2022 Poster: Maximizing Revenue under Market Shrinkage and Market Uncertainty »
Maria-Florina Balcan · Siddharth Prasad · Tuomas Sandholm -
2022 Poster: Adversarial Unlearning: Reducing Confidence Along Adversarial Directions »
Amrith Setlur · Benjamin Eysenbach · Virginia Smith · Sergey Levine -
2022 Poster: Learning Predictions for Algorithms with Predictions »
Misha Khodak · Maria-Florina Balcan · Ameet Talwalkar · Sergei Vassilvitskii -
2022 Poster: Efficient Architecture Search for Diverse Tasks »
Junhong Shen · Misha Khodak · Ameet Talwalkar -
2022 Poster: Bayesian Persuasion for Algorithmic Recourse »
Keegan Harris · Valerie Chen · Joon Kim · Ameet Talwalkar · Hoda Heidari · Steven Wu -
2022 Poster: NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks »
Renbo Tu · Nicholas Roberts · Misha Khodak · Junhong Shen · Frederic Sala · Ameet Talwalkar -
2021 : [S9] Simulated User Studies for Explanation Evaluation »
Valerie Chen · Gregory Plumb · Nicholay Topin · Ameet S Talwalkar -
2021 : Bayesian Persuasion for Algorithmic Recourse »
Keegan Harris · Valerie Chen · Joon Sik Kim · Ameet Talwalkar · Hoda Heidari · Steven Wu -
2021 : Q&A with A/Professor Virginia Smith »
Virginia Smith -
2021 : Keynote Talk: Fair or Robust: Addressing Competing Constraints in Federated Learning (Virginia Smith) »
Virginia Smith -
2021 Poster: Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution »
Amrith Setlur · Oscar Li · Virginia Smith -
2021 Poster: Data driven semi-supervised learning »
Maria-Florina Balcan · Dravyansh Sharma -
2021 Poster: On Large-Cohort Training for Federated Learning »
Zachary Charles · Zachary Garrett · Zhouyuan Huo · Sergei Shmulyian · Virginia Smith -
2021 Poster: Rethinking Neural Operations for Diverse Tasks »
Nicholas Roberts · Mikhail Khodak · Tri Dao · Liam Li · Christopher Ré · Ameet Talwalkar -
2021 Poster: Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond »
Maria-Florina Balcan · Siddharth Prasad · Tuomas Sandholm · Ellen Vitercik -
2021 Poster: Learning-to-learn non-convex piecewise-Lipschitz functions »
Maria-Florina Balcan · Mikhail Khodak · Dravyansh Sharma · Ameet Talwalkar -
2021 Oral: Data driven semi-supervised learning »
Maria-Florina Balcan · Dravyansh Sharma -
2020 Workshop: International Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL 2020) »
Xiaolin Andy Li · Dejing Dou · Ameet Talwalkar · Hongyu Li · Jianzong Wang · Yanzhi Wang -
2020 Tutorial: (Track1) Federated Learning and Analytics: Industry Meets Academia Q&A »
Peter Kairouz · Brendan McMahan · Virginia Smith -
2020 Poster: Regularizing Black-box Models for Improved Interpretability »
Gregory Plumb · Maruan Al-Shedivat · Ángel Alexander Cabrera · Adam Perer · Eric Xing · Ameet Talwalkar -
2020 Tutorial: (Track1) Federated Learning and Analytics: Industry Meets Academia »
Brendan McMahan · Virginia Smith · Peter Kairouz -
2019 : TBD »
Ameet Talwalkar -
2019 Workshop: Workshop on Federated Learning for Data Privacy and Confidentiality »
Lixin Fan · Jakub Konečný · Yang Liu · Brendan McMahan · Virginia Smith · Han Yu -
2019 Poster: Envy-Free Classification »
Maria-Florina Balcan · Travis Dick · Ritesh Noothigattu · Ariel Procaccia -
2019 Poster: Adaptive Gradient-Based Meta-Learning Methods »
Misha Khodak · Maria-Florina Balcan · Ameet Talwalkar -
2018 : Posters (all accepted papers) + Break »
Jianyu Wang · Denis Gudovskiy · Ziheng Jiang · Michael Kaufmann · Andreea Anghel · James Bradbury · Nikolas Ioannou · Nitin Agrawal · Emma Tosch · Gyeongin Yu · Keno Fischer · Jarrett Revels · Giuseppe Siracusano · Yaoqing Yang · Jeff Johnson · Yang You · Hector Yuen · Chris Ying · Honglei Liu · Nikoli Dryden · Xiangxi Mo · Yangzihao Wang · Amit Juneja · Micah Smith · Qian Yu · pramod gupta · Deepak Narayanan · Keshav Santhanam · Tim Capes · Abdul Dakkak · Norman Mu · Ke Deng · Liam Li · Joao Carreira · Luis Remis · Deepti Raghavan · Una-May O'Reilly · Amanpreet Singh · Mahmoud (Mido) Assran · Eugene Wu · Eytan Bakshy · Jinliang Wei · Michael Innes · Viral Shah · Haibin Lin · Conrad Sanderson · Ryan Curtin · Marcus Edel -
2018 : Prof. Virginia Smith »
Virginia Smith -
2018 Poster: Model Agnostic Supervised Local Explanations »
Gregory Plumb · Denali Molitor · Ameet Talwalkar -
2018 Poster: Data-Driven Clustering via Parameterized Lloyd's Families »
Maria-Florina Balcan · Travis Dick · Colin White -
2018 Spotlight: Data-Driven Clustering via Parameterized Lloyd's Families »
Maria-Florina Balcan · Travis Dick · Colin White -
2017 : Invited Talk: Sample and Computationally Efficient Active Learning Algorithms »
Maria-Florina Balcan -
2017 Poster: Variable Importance Using Decision Trees »
Jalil Kazemitabar · Arash Amini · Adam Bloniarz · Ameet S Talwalkar -
2017 Poster: Federated Multi-Task Learning »
Virginia Smith · Chao-Kai Chiang · Maziar Sanjabi · Ameet S Talwalkar -
2017 Poster: Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions »
Maria-Florina Balcan · Hongyang Zhang -
2016 : Invited Talk: Paleo: A Performance Model for Deep Neural Networks (Ameet Talwalkar, UCLA) »
Ameet S Talwalkar -
2016 Poster: Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling »
Maria-Florina Balcan · Hongyang Zhang -
2016 Poster: Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale »
Firas Abuzaid · Joseph K Bradley · Feynman Liang · Andrew Feng · Lee Yang · Matei Zaharia · Ameet S Talwalkar -
2016 Poster: Sample Complexity of Automated Mechanism Design »
Maria-Florina Balcan · Tuomas Sandholm · Ellen Vitercik -
2014 Workshop: Distributed Machine Learning and Matrix Computations »
Reza Zadeh · Ion Stoica · Ameet S Talwalkar -
2011 Workshop: Sparse Representation and Low-rank Approximation »
Ameet S Talwalkar · Lester W Mackey · Mehryar Mohri · Michael W Mahoney · Francis Bach · Mike Davies · Remi Gribonval · Guillaume R Obozinski -
2011 Poster: Divide-and-Conquer Matrix Factorization »
Lester W Mackey · Ameet S Talwalkar · Michael Jordan -
2010 Workshop: Low-rank Methods for Large-scale Machine Learning »
Arthur Gretton · Michael W Mahoney · Mehryar Mohri · Ameet S Talwalkar -
2009 Poster: Ensemble Nystrom Method »
Sanjiv Kumar · Mehryar Mohri · Ameet S Talwalkar