paper-with-me

Papers

Single-shot Hyper-parameter Optimization for Federated Learning: A General Algorithm & Analysis

2022-02-16 · Yi Zhou, Parikshit Ram, Theodoros Salonidis, Nathalie Baracaldo, Horst Samulowitz, Heiko Ludwig

We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRface Aggregation (FLoRA), a general FL-HPO solution framework that can address use cases of tabular data and any Machine Learning (ML) model including gradient boosting training algorithms and therefore further expands the scope of FL-HPO. FLoRA enables single-shot FL-HPO: identifying a single set of good hyper-parameters that are subsequently used in a single FL training. Thus, it enables FL-HPO solutions with minimal additional communication overhead compared to FL training without HPO. We theoretically characterize the optimality gap of FL-HPO, which explicitly accounts for the heterogeneous non-IID nature of the parties' local data distributions, a dominant characteristic of FL systems. Our empirical evaluation of FLoRA for multiple ML algorithms on seven OpenML datasets demonstrates significant model accuracy improvements over the considered baseline, and robustness to increasing number of parties involved in FL-HPO training.

📄 PDF Abstract BibTeX arXiv:2202.08338

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning

2021-12-15 · Yi Zhou, Parikshit Ram, Theodoros Salonidis, Nathalie Baracaldo 외

We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss suRface Aggregation (FLoRA), the first FL-HPO solution framework that can ad…

Federated Learning

Single-shot General Hyper-parameter Optimization for Federated Learning

2023-10-27 · ICLR 2023 10 · Yi Zhou, Parikshit Ram, Theodoros Salonidis, Nathalie Baracaldo 외

We address the problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRface Aggregation (FLoRA), a general FL-HPO solution framework that can address use cases of tab…

Federated Learning

Federated Hypergradient Descent

2022-11-03 · Andrew K Kan

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 ra…

Federated LearningHyperparameter Optimization

FedNest: Federated Bilevel, Minimax, and Compositional Optimization

2022-05-04 · Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, Samet Oymak

Standard federated optimization methods successfully apply to stochastic problems with single-level structure. However, many contemporary ML problems -- including adversarial robustness, hyperparameter tuning, and actor-…

Adversarial RobustnessHyperparameter OptimizationRepresentation Learning

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing

2021-06-08 · NeurIPS 2021 12 · Mikhail Khodak, Renbo Tu, Tian Li, Liam Li 외

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 he…

Federated LearningHyperparameter OptimizationNeural Architecture Search