相关论文: Controlling Federated Learning for Covertness
We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of…
This paper introduces \texttt{FedMPDD} (\textbf{Fed}erated Learning via \textbf{M}ulti-\textbf{P}rojected \textbf{D}irectional \textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy…
We study the distributed stochastic compositional optimization problems over directed communication networks in which agents privately own a stochastic compositional objective function and collaborate to minimize the sum of all objective…
Many defensive measures in cyber security are still dominated by heuristics, catalogs of standard procedures, and best practices. Considering the case of data backup strategies, we aim towards mathematically modeling the underlying threat…
Today's high-stakes adversarial interactions feature attackers who constantly breach the ever-improving security measures. Deception mitigates the defender's loss by misleading the attacker to make suboptimal decisions. In order to formally…
Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…
Training differentially private machine learning models requires constraining an individual's contribution to the optimization process. This is achieved by clipping the $2$-norm of their gradient at a predetermined threshold prior to…
Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…
This article introduces an imitation learning method for learning maximum entropy policies that comply with constraints demonstrated by expert trajectories executing a task. The formulation of the method takes advantage of results…
The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…
This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due…
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive)…
In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained…
In applications such as recommendation systems and revenue management, it is important to predict preferences on items that have not been seen by a user or predict outcomes of comparisons among those that have never been compared. A popular…
Decentralized learning and optimization is a central problem in control that encompasses several existing and emerging applications, such as federated learning. While there exists a vast literature on this topic and most methods centered…
Decentralized optimization is typically studied under the assumption of noise-free transmission. However, real-world scenarios often involve the presence of noise due to factors such as additive white Gaussian noise channels or…
Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global…
The asymptotic behavior of the stochastic gradient algorithm with a biased gradient estimator is analyzed. Relying on arguments based on the dynamic system theory (chain-recurrence) and the differential geometry (Yomdin theorem and…
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently…
In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the…