Search Results for author:
Found 21 papers, 2 papers with code
On the Relevance of Byzantine Robust Optimization Against Data Poisoning
It has been argued that the seemingly weaker threat model where only workers' local datasets get poisoned is more reasonable.
Tackling Byzantine Clients in Federated Learning
The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at the server in the standard $\mathsf{FedAvg}$ algorithm by a \emph{robust averaging rule}.
On the Privacy-Robustness-Utility Trilemma in Distributed Learning
The latter amortizes the dependence on the dimension in the error (caused by adversarial workers and DP), while being agnostic to the statistical properties of the data.
Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity
Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines.
Impact of Redundancy on Resilience in Distributed Optimization and Learning
In particular, we introduce the notion of $(f, r; \epsilon)$-resilience to characterize how well the true solution is approximated in the presence of up to $f$ Byzantine faulty agents, and up to $r$ slow agents (or stragglers) -- smaller $\epsilon$ represents a better approximation.
On the Impossible Safety of Large AI Models
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance.
Robust Collaborative Learning with Linear Gradient Overhead
We present MoNNA, a new algorithm that (a) is provably robust under standard assumptions and (b) has a gradient computation overhead that is linear in the fraction of faulty machines, which is conjectured to be tight.
Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums
We present \emph{RESAM (RESilient Averaging of Momentums)}, a unified framework that makes it simple to establish optimal Byzantine resilience, relying only on standard machine learning assumptions.
Utilizing Redundancy in Cost Functions for Resilience in Distributed Optimization and Learning
We demonstrate, both theoretically and empirically, the merits of our proposed redundancy model in improving the robustness of DGD against asynchronous and Byzantine agents, and their extensions to distributed stochastic gradient descent (D-SGD) for robust distributed machine learning with asynchronous and Byzantine agents.
Combining Differential Privacy and Byzantine Resilience in Distributed SGD
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning.
Byzantine Fault-Tolerance in Federated Local SGD under 2f-Redundancy
However, we do not know of any such techniques for the federated local SGD algorithm - a more commonly used method for federated machine learning.
On Accelerating Distributed Convex Optimizations
The system comprises multiple agents in this problem, each with a set of local data points and an associated local cost function.
Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
This paper addresses the problem of combining Byzantine resilience with privacy in machine learning (ML).
Byzantine Fault-Tolerance in Peer-to-Peer Distributed Gradient-Descent
We consider the problem of Byzantine fault-tolerance in the peer-to-peer (P2P) distributed gradient-descent method -- a prominent algorithm for distributed optimization in a P2P system.
Distributed Optimization
Distributed, Parallel, and Cluster Computing
Robustness of Iteratively Pre-Conditioned Gradient-Descent Method: The Case of Distributed Linear Regression Problem
This paper considers the problem of multi-agent distributed linear regression in the presence of system noises.
Accelerating Distributed SGD for Linear Regression using Iterative Pre-Conditioning
The recently proposed Iteratively Pre-conditioned Gradient-descent (IPG) method has been shown to converge faster than other existing distributed algorithms that solve this problem.
Byzantine Fault-Tolerant Distributed Machine Learning Using Stochastic Gradient Descent (SGD) and Norm-Based Comparative Gradient Elimination (CGE)
We show that the CGE gradient-filter guarantees fault-tolerance against a bounded fraction of Byzantine agents under standard stochastic assumptions, and is computationally simpler compared to many existing gradient-filters such as multi-KRUM, geometric median-of-means, and the spectral filters.
Iterative Pre-Conditioning for Expediting the Gradient-Descent Method: The Distributed Linear Least-Squares Problem
In this problem, the system comprises multiple agents, each having a set of local data points, that are connected to a server.
Iterative Pre-Conditioning to Expedite the Gradient-Descent Method
In this problem, there are multiple agents in the system, and each agent only knows its local cost function.
Randomized Reactive Redundancy for Byzantine Fault-Tolerance in Parallelized Learning
The coding schemes use the concept of reactive redundancy for isolating Byzantine workers that eventually send faulty information.
Byzantine Fault Tolerant Distributed Linear Regression
This paper considers the problem of Byzantine fault tolerance in distributed linear regression in a multi-agent system.
