12 citations · 14 across the 23 of their papers we have counts for
24 papers
Acceptance-Aware Draft Model Training for Speculative Decoding
Tianhua Xia, Mugilan Ganesan, Yifei Feng +3
Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to generate multiple candidate tokens that are verified by the target model…
Post-Quantum Secure Aggregation via Code-Based Homomorphic Encryption
Sebastian Bitzer, Maximilian Egger, Mumin Liu +1
Secure aggregation lets a server learn the sum of inputs from multiple users without learning individual contributions. Recent single-server protocols achieve this with key- and me…
Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
Yue Xia, Christoph Hofmeister, Maximilian Egger +1
Federated learning (FL) shows great promise in large-scale machine learning but introduces new privacy and security challenges. We propose ByITFL and LoByITFL, two novel FL schemes…
Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
Maximilian Egger, Rawad Bitar
Ensuring resilience to Byzantine clients while maintaining the privacy of the clients' data is a fundamental challenge in federated learning (FL). When the clients' data is homogen…
Efficient Machine Unlearning by Model Splitting and Core Sample Selection
Maximilian Egger, Rawad Bitar, Rüdiger Urbanke
Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon reque…
Multi-Terminal Remote Generation and Estimation Over a Broadcast Channel With Correlated Priors
Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh +2
We study the multi-terminal remote estimation problem under a rate constraint, in which the goal of the encoder is to help each decoder estimate a function over a certain distribut…
Source Anonymity for Private Random Walk Decentralized Learning
Maximilian Egger, Svenja Lage, Rawad Bitar +1
This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbo…
Federated One-Shot Learning with Data Privacy and Objective-Hiding
Maximilian Egger, Rüdiger Urbanke, Rawad Bitar
Privacy in federated learning is crucial, encompassing two key aspects: safeguarding the privacy of clients' data and maintaining the privacy of the federator's objective from the…
BICompFL: Stochastic Federated Learning with Bi-Directional Compression
Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh +2
We address the prominent communication bottleneck in federated learning (FL). We specifically consider stochastic FL, in which models or compressed model updates are specified by d…
Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning
Maximilian Egger, Mayank Bakshi, Rawad Bitar
We introduce CyBeR-0, a Byzantine-resilient federated zero-order optimization method that is robust under Byzantine attacks and provides significant savings in uplink and downlink…
Scalable and Reliable Over-the-Air Federated Edge Learning
Maximilian Egger, Christoph Hofmeister, Cem Kaya +2
Federated edge learning (FEEL) has emerged as a core paradigm for large-scale optimization. However, FEEL still suffers from a communication bottleneck due to the transmission of h…
Self-Regulating Random Walks for Resilient Decentralized Learning on Graphs
Maximilian Egger, Rawad Bitar, Ghadir Ayache +2
Consider the setting of multiple random walks (RWs) on a graph executing a certain computational task. For instance, in decentralized learning via RWs, a model is updated at each i…
Capacity-Maximizing Input Symbol Selection for Discrete Memoryless Channels
Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh +2
Motivated by communication systems with constrained complexity, we consider the problem of input symbol selection for discrete memoryless channels (DMCs). Given a DMC, the goal is…
Communication-Efficient Byzantine-Resilient Federated Zero-Order Optimization
Afonso de Sá Delgado Neto, Maximilian Egger, Mayank Bakshi +1
We introduce CYBER-0, the first zero-order optimization algorithm for memory-and-communication efficient Federated Learning, resilient to Byzantine faults. We show through extensiv…
LoByITFL: Low Communication Secure and Private Federated Learning
Yue Xia, Maximilian Egger, Christoph Hofmeister +1
Privacy of the clients' data and security against Byzantine clients are key challenges in Federated Learning (FL). Existing solutions to joint privacy and security incur sacrifices…
Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises
Yue Xia, Christoph Hofmeister, Maximilian Egger +1
Federated learning (FL) shows great promise in large scale machine learning, but brings new risks in terms of privacy and security. We propose ByITFL, a novel scheme for FL that pr…
Maximal-Capacity Discrete Memoryless Channel Identification
Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh +2
The problem of identifying the channel with the highest capacity among several discrete memoryless channels (DMCs) is considered. The problem is cast as a pure-exploration multi-ar…
Sparsity and Privacy in Secret Sharing: A Fundamental Trade-Off
Rawad Bitar, Maximilian Egger, Antonia Wachter-Zeh +1
This work investigates the design of sparse secret sharing schemes that encode a sparse private matrix into sparse shares. This investigation is motivated by distributed computing,…
Sparse and Private Distributed Matrix Multiplication with Straggler Tolerance
Maximilian Egger, Marvin Xhemrishi, Antonia Wachter-Zeh +1
This paper considers the problem of outsourcing the multiplication of two private and sparse matrices to untrusted workers. Secret sharing schemes can be used to tolerate straggler…
Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusion
Maximilian Egger, Christoph Hofmeister, Antonia Wachter-Zeh +1
In federated learning, a federator coordinates the training of a model, e.g., a neural network, on privately owned data held by several participating clients. The gradient descent…
Fast and Straggler-Tolerant Distributed SGD with Reduced Computation Load
Maximilian Egger, Serge Kas Hanna, Rawad Bitar
In distributed machine learning, a central node outsources computationally expensive calculations to external worker nodes. The properties of optimization procedures like stochasti…
Nested Gradient Codes for Straggler Mitigation in Distributed Machine Learning
Luis Maßny, Christoph Hofmeister, Maximilian Egger +2
We consider distributed learning in the presence of slow and unresponsive worker nodes, referred to as stragglers. In order to mitigate the effect of stragglers, gradient coding re…
Efficient Private Storage of Sparse Machine Learning Data
Marvin Xhemrishi, Maximilian Egger, Rawad Bitar
We consider the problem of maintaining sparsity in private distributed storage of confidential machine learning data. In many applications, e.g., face recognition, the data used in…
Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits
Maximilian Egger, Rawad Bitar, Antonia Wachter-Zeh +1
We consider the distributed SGD problem, where a main node distributes gradient calculations among workers. By assigning tasks to all the workers and waiting only for the f…