Adversarial Multi-Agent Target Tracking with Inexact Online Gradient Descent

Bedi, Amrit Singh; Sarma, P.S.; Rajawat, Ketan

doi:10.1109/icassp.2018.8461346

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the regret bound to be meaningful, it is necessary that E T be sublinear in T , a common requirement when studying online algorithms [49,50]. Sublinearly accumulating error is also natural, for instance, in the ocean environment, where noise filtering techniques can be used to drive the systematic measurement errors to zero, at least after a few iterations.…”

Section: Regret Bounds and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments

Nutalapati¹,

Bedi²,

Rajawat³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Section: Regret Bounds and Analysismentioning

confidence: 99%

“…to yield a sublinear regret. It remains open to see if (A1) can be relaxed to allow weaker conditions like error bound [49]. Remark 3.…”

Section: Regret Bounds and Analysismentioning

confidence: 99%

Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments

Nutalapati¹,

Bedi²,

Rajawat³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

“…Finally, the related problem of target tracking has been considered in the context of signal processing as well in online learning [35], [36]. Within this context, it is common to assess the performance of online algorithms using the notion of dynamic regret, that quantifies the difference between the the cost achieved by the online algorithm and that achieved by an adaptive adversary [11].…”

Section: A Related Work and Contributionsmentioning

confidence: 99%

An Online Approach to D2D Trajectory Utility Maximization Problem

Bedi

Rajawat

Coupechoux

2018

IEEE INFOCOM 2018 - IEEE Conference on Computer Communications

Self Cite

View full text Add to dashboard Cite

This paper considers the problem of designing the user trajectory in a device-to-device communications setting. We consider a pair of pedestrians connected through a D2D link. The pedestrians seek to reach their respective destinations, while using the D2D link for data exchange applications such as file transfer, video calling, and online gaming. In order to enable better D2D connectivity, the pedestrians are willing to deviate from their respective shortest paths, at the cost of reaching their destinations slightly late. A generic trajectory optimization problem is formulated and solved for the case when full information about the problem in known in advance.Motivated by the D2D user's need to keep their destinations private, we also formulate a regularized variant of the problem that can be used to develop a fully online algorithm. The proposed online algorithm is quite efficient, and is shown to achieve a sublinear offline regret while satisfying the required mobility constraints exactly. The theoretical results are backed by detailed numerical tests that establish the efficacy of the proposed algorithms under various settings.

show abstract

Defending non-Bayesian learning against adversarial attacks

Vaidya

2018

Distrib. Comput.

View full text Add to dashboard Cite

This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We focus on the impact of the adversarial agents on the performance of consensus-based non-Bayesian learning, where non-faulty agents combine local learning updates with consensus primitives. In particular, we consider the scenario where an unknown subset of agents suffer Byzantine faults -agents suffering Byzantine faults behave arbitrarily.We propose two learning rules.-In our first update rule, each agent updates its local beliefs as (up to normalization) the product of (1) the likelihood of the cumulative private signals and (2) the weighted geometric average of the beliefs of its incoming neighbors and itself. Under reasonable assumptions on the underlying network structure and the global identifiability of the network, we show that all the non-faulty agents asymptotically agree on the true state almost surely. For the case when every agent is failure-free, we show that (with high probability) each agent's beliefs on the wrong hypotheses decrease at rate O(exp(−Ct 2 )), where t is the number of iterations, and C is a constant. -In general when agents may be adversarial, network identifiability condition specified for the above learning rule scales poorly in the number of state candidates m. In addition, the computation complexity per agent per iteration of this learning rule is forbiddingly high. Thus, we propose a modification of our first learning rule, whose complexity per iteration per agent is O(m 2 n log n), where n is the number of agents in the network. We show that this modified learning rule works under a much weaker network identifiability condition. In addition, this new condition is independent of m.⋆

show abstract

Adversarial Multi-Agent Target Tracking with Inexact Online Gradient Descent

Cited by 5 publications

References 0 publications

Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments

Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments

An Online Approach to D2D Trajectory Utility Maximization Problem

Defending non-Bayesian learning against adversarial attacks

Contact Info

Product

Resources

About