References & Further Reading

References

Y. Chen, A. R. Elkordy, and A. S. Avestimehr, A Survey on Information-Theoretic Approaches to Secure and Private Federated Learning, 2023
Comprehensive review of the information-theoretic frontier of secure FL. Maps the open problems of this chapter.
Q. Yu, M. A. Maddah-Ali, and A. S. Avestimehr, Straggler Mitigation in Distributed Optimization Through Data Encoding, 2020
Polynomial approach to non-linear coded computing. Basis for §18.1.
J. Kosaian, K. Rashmi, and S. Venkataraman, Parity Models: Erasure-Coded Resilience for Prediction Serving Systems, 2020
Learned coded computing for non-linear functions. Referenced in §18.1.
S. Dutta, Z. Bai, T. Yun, G. Suh, and P. Grover, Short-Dot Products and Hybrid Coded Computing, 2020
Hybrid coded-uncoded schemes for non-linear coded computing. Referenced in §18.1.
T. Jahani-Nezhad, M. A. Maddah-Ali, S. Li, and G. Caire, Byzantine-Resilient Secure Aggregation for Federated Learning With Consistency Guarantees, 2022
ByzSecAgg: jointly privacy + robustness. Referenced in §18.2.
P. Kairouz et al., Advances and Open Problems in Federated Learning, 2021
Comprehensive FL survey. Open problems discussed in §18.2, §18.4.
P. Blanchard, E. M. E. Mhamdi, R. Guerraoui, and J. Stainer, Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent, 2017
Krum and aggregation-level Byzantine-resilience. Referenced in §18.2.
X. Lian, C. Zhang, H. Zhang, C.-J. Hsieh, W. Zhang, and J. Liu, Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent, 2017
Foundational D-SGD. Basis for §18.3.
A. Lalitha, S. Shekhar, T. Javidi, and F. Koushanfar, Fully Decentralized Federated Learning, 2018
Sparse D-SGD with graph-based gossip. Referenced in §18.3.
R. Bommasani et al., On the Opportunities and Risks of Foundation Models, 2021
Survey of modern ML landscape (foundation models, transformers, MoE). Motivates the §18.4 frontiers.
Y. Lu, C. Jia, K. Naouss, and P. Torr, Coded Attention for Transformer Acceleration, 2023
Early work on coded transformer attention. §18.4 frontier.
N. Shazeer et al., Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, 2017
The foundational MoE paper. Referenced in §18.4 on coded MoE.
P. Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, 2020
The RAG paper. Referenced in §18.4 for the PIR connection.
S. Song and M. Hayashi, Capacity of Quantum Private Information Retrieval with Multiple Servers, 2019
Quantum PIR capacity. Referenced in §18.4.
M. Allaix, S. Song, L. Holzbaur, T. Pllaha, M. Hayashi, and C. Hollanti, On the Capacity of Quantum Private Information Retrieval From MDS-Coded and Colluding Servers, 2022
Quantum advantage in $T$-colluding coded-storage PIR. Theorem 18.4.1.