A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks

Mitra, Arindam; Richards, John A.; Sundaram, Shreyas

doi:10.1109/cdc40024.2019.9029838

Cited by 14 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, [27] and [28] make novel connectivity assumptions, but unlike our work, neither of them allows for arbi-trarily long periods of poor (or zero) network connectivity. The same can be said about [18] and [29], even though they consider random graphs/digraphs and impose connectivity criteria only in the expectation sense.…”

Section: Introductionmentioning

confidence: 99%

Non-Bayesian Social Learning on Random Digraphs with Aperiodically Varying Network Connectivity

Parasnis¹,

Franceschetti²,

Touri³

2020

Preprint

View full text Add to dashboard Cite

We study non-Bayesian social learning on random directed graphs and show that under mild assumptions on the connectivity of the network, all the agents almost surely learn the true state of the world asymptotically in time if the sequence of the associated weighted adjacency matrices belongs to Class P * (a broad class of stochastic chains that subsumes uniformly strongly connected chains). We show that though uniform strong connectivity is not necessary for asymptotic learning, it helps ensure that all the agents' beliefs converge to a consensus almost surely even when the true state is not identifiable. We then show how our main result applies to a few variants of the original model such as inertial non-Bayesian learning and learning in the presence of link failures. Besides, we show that our main result is an extension of a few known results that pertain to learning on time-varying graphs. We also show by proof and an example that if the network of influences is balanced in a certain sense, then asymptotic learning occurs almost surely even in the absence of uniform strong connectivity.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Bayesian Social Learning on Random Digraphs with Aperiodically Varying Network Connectivity

Parasnis¹,

Franceschetti²,

Touri³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Combining the analyses of cases 1 and 2, referring to ( 13) and ( 15), and noting that γ(t) ∈ (0, 1], ∀t ∈ N, we conclude that the bound in (15) holds for each t k ∈ I such that t k > tv . Now since t k+1 − t k = g(k), for any τ ∈ N + we have:…”

Section: Proofsmentioning

confidence: 75%

“…In particular, without the event condition in Eq. 4, our communication strategy would boil down to a simple time-triggered rule, akin to the one studied in our recent work [15].…”

Section: An Event-triggered Distributed Learning Rulementioning

confidence: 99%

See 1 more Smart Citation

Event-Triggered Distributed Inference

Mitra

Bagchi

Sundaram

2020

2020 59th IEEE Conference on Decision and Control (CDC)

Self Cite

View full text Add to dashboard Cite

We study a setting where each agent in a network receives certain private signals generated by an unknown static state that belongs to a finite set of hypotheses. The agents are tasked with collectively identifying the true state. To solve this problem in a communication-efficient manner, we propose an event-triggered distributed learning algorithm that is based on the principle of diffusing low beliefs on each false hypothesis. Building on this principle, we design a trigger condition under which an agent broadcasts only those components of its belief vector that have adequate innovation, to only those neighbors that require such information. We establish that under standard assumptions, each agent learns the true state exponentially fast almost surely. We also identify sparse communication regimes where the inter-communication intervals grow unbounded, and yet, the asymptotic learning rate of our algorithm remains the same as the best known rate for this problem. We then establish, both in theory and via simulations, that our event-triggering strategy has the potential to significantly reduce information flow from uninformative agents to informative agents. Finally, we argue that, as far as only asymptotic learning is concerned, one can allow for arbitrarily sparse communication patterns.

show abstract

“…In this context, one ripe candidate problem is that of hypothesis-testing/statistical inference where the true hypothesis belongs to a finite set of possible hypotheses. Recent results have shown that for peer-to-peer versions of this problem [88,89], one can design principled approaches to significantly reduce communication.…”

Section: Discussionmentioning

confidence: 99%

Exploiting Heterogeneity in Robust Federated Best-Arm Identification

Mitra¹,

Hassani²,

Pappas³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We study a federated variant of the best-arm identification problem in stochastic multiarmed bandits: a set of clients, each of whom can sample only a subset of the arms, collaborate via a server to identify the best arm (i.e., the arm with the highest mean reward) with prescribed confidence. For this problem, we propose Fed-SEL, a simple communication-efficient algorithm that builds on successive elimination techniques and involves local sampling steps at the clients. To study the performance of Fed-SEL, we introduce a notion of arm-heterogeneity that captures the level of dissimilarity between distributions of arms corresponding to different clients. Interestingly, our analysis reveals the benefits of arm-heterogeneity in reducing both the sample-and communication-complexity of Fed-SEL. As a special case of our analysis, we show that for certain heterogeneous problem instances, Fed-SEL outputs the best-arm after just one round of communication. Our findings have the following key implication: unlike federated supervised learning where recent work has shown that statistical heterogeneity can lead to poor performance, one can provably reap the benefits of both local computation and heterogeneity for federated best-arm identification. As our final contribution, we develop variants of Fed-SEL, both for federated and peer-to-peer settings, that are robust to the presence of Byzantine clients, and hence suitable for deployment in harsh, adversarial environments.

show abstract

A Communication-Efficient Algorithm for Exponentially Fast Non-Bayesian Learning in Networks

Cited by 14 publications

References 18 publications

Non-Bayesian Social Learning on Random Digraphs with Aperiodically Varying Network Connectivity

Non-Bayesian Social Learning on Random Digraphs with Aperiodically Varying Network Connectivity

Event-Triggered Distributed Inference

Exploiting Heterogeneity in Robust Federated Best-Arm Identification

Contact Info

Product

Resources

About