# Federated Hypergradient Descent

arXiv: https://arxiv.org/abs/2211.02106 · HTML: https://mlsanity.com/paper/2211.02106/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning](https://mlsanity.com/paper/2101.11203/) (2021)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [Online Learning Rate Adaptation with Hypergradient Descent](https://mlsanity.com/paper/1703.04782/) (2017)
- [Local SGD: Unified Theory and New Efficient Methods](https://mlsanity.com/paper/2011.02828/) (2020)
- [Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD](https://mlsanity.com/paper/1810.08313/) (2018)
- [Federated Bayesian Optimization via Thompson Sampling](https://mlsanity.com/paper/2010.10154/) (2020)
- [Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing](https://mlsanity.com/paper/2106.04502/) (2021)
- [Geometry-Aware Gradient Algorithms for Neural Architecture Search](https://mlsanity.com/paper/2004.07802/) (2020)
- [On the Outsized Importance of Learning Rates in Local Update Methods](https://mlsanity.com/paper/2007.00878/) (2020)
- [Exponentiated Gradient Meets Gradient Descent](https://mlsanity.com/paper/1902.01903/) (2019)
- [FedJAX: Federated learning simulation with JAX](https://mlsanity.com/paper/2108.02117/) (2021)
- [Differentially Private Federated Bayesian Optimization with Distributed Exploration](https://mlsanity.com/paper/2110.14153/) (2021)
- [Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters](https://mlsanity.com/paper/1912.13075/) (2019)
- [Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation](https://mlsanity.com/paper/2203.06338/) (2022)
- [Evaluation of Hyperparameter-Optimization Approaches in an Industrial Federated Learning System](https://mlsanity.com/paper/2110.08202/) (2021)
- [Convergence of the Exponentiated Gradient Method with Armijo Line Search](https://mlsanity.com/paper/1712.08480/) (2017)
- [Step-size Adaptation Using Exponentiated Gradient Updates](https://mlsanity.com/paper/2202.00145/) (2022)
- [FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization](https://mlsanity.com/paper/2206.03966/) (2022)
- [Single-shot Hyper-parameter Optimization for Federated Learning: A General Algorithm & Analysis](https://mlsanity.com/paper/2202.08338/) (2022)

## Built on by (most cited first, 2 of 2)

- [FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent](https://mlsanity.com/paper/2310.03156/) (2023)
- [Federated Automatic Differentiation](https://mlsanity.com/paper/2301.07806/) (2023)

## Abstract (arXiv)

In this work, we explore combining automatic hyperparameter tuning and optimization for federated learning (FL) in an online, one-shot procedure. We apply a principled approach on a method for adaptive client learning rate, number of local steps, and batch size. In our federated learning applications, our primary motivations are minimizing communication budget as well as local computational resources in the training pipeline. Conventionally, hyperparameter tuning methods involve at least some degree of trial-and-error, which is known to be sample inefficient. In order to address our motivations, we propose FATHOM (Federated AuTomatic Hyperparameter OptiMization) as a one-shot online procedure. We investigate the challenges and solutions of deriving analytical gradients with respect to the hyperparameters of interest. Our approach is inspired by the fact that, with the exception of local data, we have full knowledge of all components involved in our training process, and this fact can be exploited in our algorithm impactfully. We show that FATHOM is more communication efficient than Federated Averaging (FedAvg) with optimized, static valued hyperparameters, and is also more computationally efficient overall. As a communication efficient, one-shot online procedure, FATHOM solves the bottleneck of costly communication and limited local computation, by eliminating a potentially wasteful tuning process, and by optimizing the hyperparamters adaptively throughout the training procedure without trial-and-error. We show our numerical results through extensive empirical experiments with the Federated EMNIST-62 (FEMNIST) and Federated Stack Overflow (FSO) datasets, using FedJAX as our baseline framework.