Theoretically Principled Federated Learning for Balancing Privacy and Utility
cs.LG, cs.AI, cs.CR
Submitted: 2023-05-24
Updated: 2026-08-26
Code: https://github.com/JonasGeiping/invertinggradients
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Federated Learning: Strategies for Improving Communication Efficiency
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- iDLG: Improved Deep Leakage from Gradients
- Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
- No Free Lunch Theorem for Security and Utility in Federated Learning
- Trading Off Privacy, Utility and Efficiency in Federated Learning
- Differentially Private Federated Learning: A Client Level Perspective
- Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation
- Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
- A Game-theoretic Framework for Privacy-preserving Federated Learning
- Probably Approximately Correct Federated Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks