Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Laser material processing (LMP) has revolutionized modern manufacturing, emerging as a cornerstone technology valued for its precision, speed, and versatility, especially in high-stakes sectors like aerospace, automotive, and medical device production. Des ...

Demographic fairness or equity is a crucial aspect of machine learning models, particularly in critical domains such as healthcare, where errors can have severe consequences. A fair model avoids making distinctions between groups with different sensitive o ...

A payment channel network is a blockchain-based overlay mechanism that allows parties to transact more efficiently than directly using the blockchain. These networks are composed of payment channels that carry transactions between pairs of users. Due to it ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Beliefs inform the behaviour of forward-thinking agents in complex environments. Recently, sequential Bayesian inference has emerged as a mechanism to study belief formation among agents adapting to dynamical conditions. However, we lack critical theory to ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

The scale and pervasiveness of the Internet make it a pillar of planetary communication, industry and economy, as well as a fundamental medium for public discourse and democratic engagement. In stark contrast with the Internet's decentralized infrastructur ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free metho ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinem ...

The sum-of-squares (SOS) approximation method is a technique used in optimization problems to derive lower bounds on the optimal value of an objective function. By representing the objective function as a sum of squares in a feature space, the SOS method t ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

This paper considers the problem of resilient distributed optimization and stochastic learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has its own local cost function. The agents collaborate with ...

A multi-agent system consists of a collection of decision-making or learning agents subjected to streaming observations from some real-world phenomenon. The goal of the system is to solve some global learning or optimization problem in a distributed or dec ...

The problem of Byzantine resilience in distributed machine learning, a.k.a., Byzantine machine learning, consists in designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes, i.e., nodes with corrupt data or ...

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

Byzantine Fault-Tolerance in Federated Local SGD Under 2f-Redundancy

Chat with Graph Search

Toward Autonomous Laser Manufacturing: Solving Key Challenges in Optimization, Monitoring, and Control

Optimizing fairness and utility in healthcare machine learning models

Pricing for Routing and Flow-control in Payment Channel Networks

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Stochastic pairwise preference convergence in Bayesian agents

Understanding generalization and robustness in modern deep learning

Planetary-Scale Byzantine Fault Tolerance

On the Generalization of Stochastic Gradient Descent with Momentum

Neural Redshift: Random Networks are not Random Functions

Revisiting Character-level Adversarial Attacks for Language Models

Social Opinion Formation and Decision Making Under Communication Trends

Topics in statistical physics of high-dimensional machine learning

Towards practical reinforcement learning for tokamak magnetic control

Theory and applications of the sum-of-squares technique

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Multi-agent Learning with Privacy Guarantees

Byzantine Machine Learning: A Primer

Phenomenological theory of variational quantum ground-state preparation

Communication-efficient distributed training of machine learning models