A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Local Differential Privacy for Regret Minimization in Reinforcement Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
We formulate this notion of privacy for RL by leveraging the local differential privacy (LDP) framework. ...
We establish a lower bound for regret minimization in finite-horizon MDPs with LDP guarantees which shows that guaranteeing privacy has a multiplicative effect on the regret. ...
G Posterior Sampling for Local Differential Privacy The Posterior Sampling for Reinforcement Learning algorithm [PSRL, Osband et al., 2013 ] is a Thompson Sampling based algorithm for Reinforcement Learning ...
arXiv:2010.07778v3
fatcat:76bncyh47zgr3bvtu5qf52gxnm
Differentially Private Regret Minimization in Episodic Markov Decision Processes
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP). ...
This is motivated by the widespread applications of reinforcement learning (RL) in real-world sequential decision making problems, where protecting users' sensitive and private information is becoming ...
Local differentially private regret
minimization in reinforcement learning. arXiv preprint arXiv:2010.07778, 2020.
Cynthia Dwork. Differential privacy: A survey of results. ...
arXiv:2112.10599v1
fatcat:nuiwxweo7vcajhfbjeiilo5zle
Shuffle Private Linear Contextual Bandits
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
However, there remains a fundamental gap in the utility achieved by learning algorithms under these two privacy models, e.g., Õ(√(T)) regret in the central model as compared to Õ(T^3/4) regret in the local ...
Differential privacy (DP) has been recently introduced to linear contextual bandits to formally address the privacy concerns in its associated personalized services to participating users (e.g., recommendations ...
Locally differentially private (contextual) bandits learning. In NeurIPS, 2020. ...
arXiv:2202.05567v1
fatcat:z5mnuy4jtvhubfitvvfccfpvke
Differentially Private Reinforcement Learning with Linear Function Approximation
2022
Proceedings of the ACM on Measurement and Analysis of Computing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in ...
a building block for general private reinforcement learning. ...
in reinforcement learning. ...
doi:10.1145/3508028
fatcat:v4u3idqfwvcd5megi3gdroalli
Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL with linear function approximation and local differential privacy (LDP) guarantees. ...
We propose a novel (ε, δ)-LDP algorithm for learning a class of Markov decision processes (MDPs) dubbed linear mixture MDPs, and obtains an 𝒪̃( d^5/4H^7/4T^3/4(log(1/δ))^1/4√(1/ε)) regret, where d is ...
(Local) Differential Privacy In this subsection, we introduce the standard definition of differential privacy (Dwork et al., 2006) and local differential privacy (Kasiviswanathan et al., 2011; Duchi ...
arXiv:2110.10133v1
fatcat:gvvkdlzxr5eylcawjdp5xrmgcy
Differentially Private Meta-Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. ...
We then propose a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex ...
ACKNOWLEDGMENTS This work was supported in part by DARPA FA875017C0141, the National Science Foundation grants IIS1618714, IIS1705121, and IIS1838017, an Okawa Grant, a Google Faculty Award, an Amazon ...
arXiv:1909.05830v2
fatcat:e37kmf6fsrdutcn2w2p5qarvxu
Multi-Armed Bandits with Local Differential Privacy
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. ...
To handle this dilemma, we adopt differential privacy and study the regret upper and lower bounds for MAB algorithms with a given LDP guarantee. ...
Mathematically, the (pseudo) regret is defined as R(T ) := T µ * − T t=1 E[µ A t ] = E[ a∈[n] N T a ∆ a ]. The goal of the agent is to minimize the regret. Local differential privacy. ...
arXiv:2007.03121v1
fatcat:eehdco6p4ndpffatetx47o4nzi
Private Reinforcement Learning with PAC and Regret Guarantees
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Finally, we present lower bounds on sample complexity and regret for reinforcement learning subject to JDP. ...
Our algorithm only pays for a moderate privacy cost on exploration: in comparison to the non-private bounds, the privacy parameter only appears in lower-order terms. ...
In this paper we contribute to the study of reinforcement learning from the lens of differential privacy. ...
arXiv:2009.09052v1
fatcat:piv3gjndg5g5lfnmnfo5qsxfuq
Corrupt Bandits for Preserving Local Privacy
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We also provide the appropriate corruption parameters to guarantee a desired level of local privacy and analyze how this impacts the regret. ...
We provide a lower bound on the expected regret of any bandit algorithm in this corrupted setting. ...
In this article, we consider local differential privacy. ...
arXiv:1708.05033v2
fatcat:wpvawzedend5tpcgft272z7v3q
Local Differential Privacy and Its Applications: A Comprehensive Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Local differential privacy (LDP), as a strong privacy tool, has been widely deployed in the real world in recent years. ...
We discuss the practical deployment of local differential privacy and explore its application in various domains. ...
[91] propose a local differential privacy algorithm based on asynchronous advantage actor-critic (A3C) for distributed reinforcement learning to obtain a robust policy. ...
arXiv:2008.03686v1
fatcat:l7z3gip2ivdmvin7lraxd4vciy
Byzantine-Robust Federated Linear Bandits
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. ...
Finally, if the level of corruption is known to be small, we show that using the geometric median of mean oracle for robust aggregation further improves the regret bound. ...
Differential privacy. Privacy issues are also important for distributed systems. ...
arXiv:2204.01155v1
fatcat:64deqod4xfcmnbj34jtybxvzpa
Federated Bandit: A Gossiping Approach
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We then propose Fed_UCB, a differentially private version of Gossip_UCB, in which the agents preserve ϵ-differential privacy of their local data while achieving O(max{poly(N,M)/ϵlog^2.5 T, poly(N,M) (log_λ ...
We show that Gossip_UCB successfully adapts local bandit learning into a global gossiping process for sharing information among connected agents, and achieves guaranteed regret at the order of O(max{poly ...
through gossiping, and its differentially private variant, Fed_UCB, for preserving -differential privacy of the agents' local data. ...
arXiv:2010.12763v1
fatcat:skq7homjy5cs5phj3ikbcda2r4
Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learning
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Finally, we complete the survey by providing an outlook on the challenges and possible directions for future research in this critical area. ...
In this paper, we provide a survey of the emerging security and privacy risks of distributed ML from a unique perspective of information exchange levels, which are defined according to the key steps of ...
Differential Privacy Differential privacy (DP) is a standard definition for privacy estimation [130] . ...
arXiv:2202.09027v2
fatcat:hlu7bopcjrc6zjn2pct57utufy
A Comprehensive Survey of Incentive Mechanism for Federated Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a comprehensive survey of incentive schemes for federate learning. ...
Specifically, we identify the incentive problem in federated learning and then provide a taxonomy for various schemes. ...
In sum, reinforcement learning can be innovatively applied for the incentive design in FL. ...
arXiv:2106.15406v1
fatcat:7v7adaw5wnbldhykma6mhgpnty
Interactive Sensing and Decision Making in Social Networks
2014
Foundations and Trends® in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This monograph provides a survey, tutorial development, and discussion of four highly stylized examples: social learning for interactive sensing; tracking the degree distribution of social networks; sensing ...
and information diffusion; and coordination of decision making via game-theoretic learning. ...
In social learning, each agent chooses its action by optimizing its local utility function. ...
doi:10.1561/2000000048
fatcat:5hr4ebohczhrlolw4whenlicj4
« Previous
Showing results 1 — 15 out of 3,935 results