Timezone: »
Privacy costs may negate the benefits of using adaptive optimizers in differentially private model training. Prior works typically address this issue by using auxiliary information (e.g., public data) to boost the effectiveness of adaptive optimization. In this work, we explore techniques to estimate and efficiently adapt to gradient geometry in private adaptive optimization without auxiliary data. Motivated by the observation that adaptive methods can tolerate stale preconditioners, we propose differentially private adaptive training with delayed preconditioners (DP^2), a simple method that constructs delayed but less noisy preconditioners to better realize the benefits of adaptivity. Theoretically, we provide convergence guarantees for our method for both convex and non-convex problems, and analyze trade-offs between delay and privacy noise reduction. Empirically, we explore DP^2 across several real-world datasets, demonstrating that it can improve convergence speed by as much as 4× relative to non-adaptive baselines and match the performance of state-of-the-art optimization methods that require auxiliary data.
Author Information
Tian Li (CMU)
Manzil Zaheer (Google)
Ken Liu (Carnegie Mellon University)
Sashank Reddi (Google)
H. Brendan McMahan (Google, Inc.)
Virginia Smith (Carnegie Mellon University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 : Differentially Private Adaptive Optimization with Delayed Preconditioners »
Dates n/a. Room
More from the Same Authors
-
2022 : Motley: Benchmarking Heterogeneity and Personalization in Federated Learning »
Shanshan Wu · Tian Li · Zachary Charles · Yu Xiao · Ken Liu · Zheng Xu · Virginia Smith -
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 : An Empirical Evaluation of Federated Contextual Bandit Algorithms »
Alekh Agarwal · H. Brendan McMahan · Zheng Xu -
2023 : One-shot Empirical Privacy Estimation for Federated Learning »
Galen Andrew · Peter Kairouz · Sewoong Oh · Alina Oprea · H. Brendan McMahan · Vinith Suriyakumar -
2023 : Efficient Stagewise Pretraining via Progressive Subnetworks »
Abhishek Panigrahi · Nikunj Saunshi · Kaifeng Lyu · Sobhan Miryoosefi · Sashank Reddi · Satyen Kale · Sanjiv Kumar -
2023 : Evaluating Large-Scale Learning Systems, Virginia Smith »
Virginia Smith -
2023 : Virginia Smith - On Privacy and Personalization in Federated Learning »
Virginia Smith -
2023 Poster: (Amplified) Banded Matrix Factorization: A unified approach to private training »
Christopher A. Choquette-Choo · Arun Ganesh · Ryan McKenna · H. Brendan McMahan · John Rush · Abhradeep Guha Thakurta · Zheng Xu -
2023 Poster: Progressive Ensemble Distillation: Building 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: Unleashing the Power of Randomization in Auditing Differentially Private ML »
Krishna Pillutla · Galen Andrew · Peter Kairouz · H. Brendan McMahan · Alina Oprea · Sewoong Oh -
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: ResMem: Learn what you can and memorize the rest »
Zitong Yang · MICHAL LUKASIK · Vaishnavh Nagarajan · Zonglin Li · Ankit Rawat · Manzil Zaheer · Aditya Menon · Sanjiv Kumar -
2023 Poster: What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models »
Khashayar Gatmiry · Zhiyuan Li · Tengyu Ma · Sashank Reddi · Stefanie Jegelka · Ching-Yao Chuang -
2023 Poster: Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy »
Anastasiia Koloskova · Ryan McKenna · Zachary Charles · John Rush · H. Brendan McMahan -
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: Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams »
Sergey Denisov · H. Brendan McMahan · John Rush · Adam Smith · Abhradeep Guha Thakurta -
2022 Poster: On Privacy and Personalization in Cross-Silo Federated Learning »
Ken Liu · Shengyuan Hu · Steven Wu · Virginia Smith -
2022 Poster: A Fourier Approach to Mixture Learning »
Mingda Qiao · Guru Guruganesh · Ankit Rawat · Kumar Avinava Dubey · Manzil Zaheer -
2022 Poster: Adversarial Unlearning: Reducing Confidence Along Adversarial Directions »
Amrith Setlur · Benjamin Eysenbach · Virginia Smith · Sergey Levine -
2022 Poster: Learning to Navigate Wikipedia by Taking Random Walks »
Manzil Zaheer · Kenneth Marino · Will Grathwohl · John Schultz · Wendy Shang · Sheila Babayan · Arun Ahuja · Ishita Dasgupta · Christine Kaeser-Chen · Rob Fergus -
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: No Regrets for Learning the Prior in Bandits »
Soumya Basu · Branislav Kveton · Manzil Zaheer · Csaba Szepesvari -
2021 Poster: Breaking the centralized barrier for cross-device federated learning »
Sai Praneeth Karimireddy · Martin Jaggi · Satyen Kale · Mehryar Mohri · Sashank Reddi · Sebastian Stich · Ananda Theertha Suresh -
2021 Poster: The Skellam Mechanism for Differentially Private Federated Learning »
Naman Agarwal · Peter Kairouz · Ken Liu -
2021 Poster: On Large-Cohort Training for Federated Learning »
Zachary Charles · Zachary Garrett · Zhouyuan Huo · Sergei Shmulyian · Virginia Smith -
2021 Poster: Efficient Training of Retrieval Models using Negative Cache »
Erik Lindgren · Sashank Reddi · Ruiqi Guo · Sanjiv Kumar -
2021 Poster: Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing »
Mikhail Khodak · Renbo Tu · Tian Li · Liam Li · Maria-Florina Balcan · Virginia Smith · Ameet Talwalkar -
2020 Tutorial: (Track1) Federated Learning and Analytics: Industry Meets Academia Q&A »
Peter Kairouz · Brendan McMahan · Virginia Smith -
2020 Poster: PLLay: Efficient Topological Layer based on Persistent Landscapes »
Kwangho Kim · Jisu Kim · Manzil Zaheer · Joon Kim · Frederic Chazal · Larry Wasserman -
2020 Poster: Why are Adaptive Methods Good for Attention Models? »
Jingzhao Zhang · Sai Praneeth Karimireddy · Andreas Veit · Seungyeon Kim · Sashank Reddi · Sanjiv Kumar · Suvrit Sra -
2020 Poster: O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers »
Chulhee Yun · Yin-Wen Chang · Srinadh Bhojanapalli · Ankit Singh Rawat · Sashank Reddi · Sanjiv Kumar -
2020 Poster: Differentiable Meta-Learning of Bandit Policies »
Craig Boutilier · Chih-wei Hsu · Branislav Kveton · Martin Mladenov · Csaba Szepesvari · Manzil Zaheer -
2020 Poster: Latent Bandits Revisited »
Joey Hong · Branislav Kveton · Manzil Zaheer · Yinlam Chow · Amr Ahmed · Craig Boutilier -
2020 Poster: Robust large-margin learning in hyperbolic space »
Melanie Weber · Manzil Zaheer · Ankit Singh Rawat · Aditya Menon · Sanjiv Kumar -
2020 Poster: Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning »
Meng Zhou · Ken Liu · Pengwei Sui · Yixuan Li · Yuk Ying Chung -
2020 Poster: Big Bird: Transformers for Longer Sequences »
Manzil Zaheer · Guru Guruganesh · Kumar Avinava Dubey · Joshua Ainslie · Chris Alberti · Santiago Ontanon · Philip Pham · Anirudh Ravula · Qifan Wang · Li Yang · Amr Ahmed -
2020 Tutorial: (Track1) Federated Learning and Analytics: Industry Meets Academia »
Brendan McMahan · Virginia Smith · Peter Kairouz -
2019 : Coffee Break & Poster Session 1 »
Yan Zhang · Jonathon Hare · Adam Prugel-Bennett · Po Leung · Patrick Flaherty · Pitchaya Wiratchotisatian · Alessandro Epasto · Silvio Lattanzi · Sergei Vassilvitskii · Morteza Zadimoghaddam · Theja Tulabandhula · Fabian Fuchs · Adam Kosiorek · Ingmar Posner · William Hang · Anna Goldie · Sujith Ravi · Azalia Mirhoseini · Yuwen Xiong · Mengye Ren · Renjie Liao · Raquel Urtasun · Haici Zhang · Michele Borassi · Shengda Luo · Andrew Trapp · Geoffroy Dubourg-Felonneau · Yasmeen Kussad · Christopher Bender · Manzil Zaheer · Junier Oliva · Michał Stypułkowski · Maciej Zieba · Austin Dill · Chun-Liang Li · Songwei Ge · Eunsu Kang · Oiwi Parker Jones · Kelvin Ka Wing Wong · Joshua Payne · Yang Li · Azade Nazi · Erkut Erdem · Aykut Erdem · Kevin O'Connor · Juan J Garcia · Maciej Zamorski · Jan Chorowski · Deeksha Sinha · Harry Clifford · John W Cassidy -
2019 : Opening Remarks »
Manzil Zaheer · Nicholas Monath · Ari Kobren · Junier Oliva · Barnabas Poczos · Ruslan Salakhutdinov · Andrew McCallum -
2019 Workshop: Sets and Partitions »
Nicholas Monath · Manzil Zaheer · Andrew McCallum · Ari Kobren · Junier Oliva · Barnabas Poczos · Ruslan Salakhutdinov -
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: Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces »
Chuan Guo · Ali Mousavi · Xiang Wu · Daniel Holtmann-Rice · Satyen Kale · Sashank Reddi · Sanjiv Kumar -
2019 Poster: Multilabel reductions: what is my loss optimising? »
Aditya Menon · Ankit Singh Rawat · Sashank Reddi · Sanjiv Kumar -
2019 Spotlight: Multilabel reductions: what is my loss optimising? »
Aditya Menon · Ankit Singh Rawat · Sashank Reddi · Sanjiv Kumar -
2018 : Prof. Virginia Smith »
Virginia Smith -
2018 Poster: Nonparametric Density Estimation under Adversarial Losses »
Shashank Singh · Ananya Uppal · Boyue Li · Chun-Liang Li · Manzil Zaheer · Barnabas Poczos -
2018 Poster: Adaptive Methods for Nonconvex Optimization »
Manzil Zaheer · Sashank Reddi · Devendra S Sachan · Satyen Kale · Sanjiv Kumar -
2017 Oral: Deep Sets »
Manzil Zaheer · Satwik Kottur · Siamak Ravanbakhsh · Barnabas Poczos · Ruslan Salakhutdinov · Alexander Smola -
2017 Poster: Deep Sets »
Manzil Zaheer · Satwik Kottur · Siamak Ravanbakhsh · Barnabas Poczos · Ruslan Salakhutdinov · Alexander Smola -
2007 Spotlight: Selecting Observations against Adversarial Objectives »
Andreas Krause · H. Brendan McMahan · Carlos Guestrin · Anupam Gupta -
2007 Poster: Selecting Observations against Adversarial Objectives »
Andreas Krause · H. Brendan McMahan · Carlos Guestrin · Anupam Gupta