arXiv research

New method reduces regret and communication costs in federated Q-learning.

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities $\frac{a}{n}$ and $\frac{b}{n}$ respectively. We consider the sparse setting, in which $a$ and $b$ do not scale with $n$, and…

Study on individual regret in cooperative MAB with agents communicating over a graph.

Paper studies signal detection in noisy environments with limited communication.

Paper studies fundamental limits of communication in distributed learning.

Distributed Thompson sampling improves regret convergence in constrained communication networks.

Study on efficient estimation of Gaussian mean with limited communication.

New estimator for overlapping community detection in graphs.

The paper provides bounds on estimation error in a distributed online learning setting.

We prove a general connection between the communication complexity of two-player games and the sample complexity of their multi-player locally private analogues. We use this connection to prove sample complexity lower bounds for locally differentially private protocols as straightforward corollaries of results from com…

Study recovers community structure from coarse graph measurements.

Improved algorithm reduces communication rounds for distributed online learning.

Recently, there has been an increasing interest in designing distributed convex optimization algorithms under the setting where the data matrix is partitioned on features. Algorithms under this setting sometimes have many advantages over those under the setting where data is partitioned on samples, especially when the …

In this paper, we study the sensitivity of the spectral clustering based community detection algorithm subject to a Erdos-Renyi type random noise model. We prove phase transitions in community detectability as a function of the external edge connection probability and the noisy edge presence probability under a general…

We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from off…

Study information limits for community detection in sub-hypergraphs.

We introduce the concept of community trees that summarizes topological structures within a network. A community tree is a tree structure representing clique communities from the clique percolation method (CPM). The community tree also generates a persistent diagram. Community trees and persistent diagrams reveal topol…

Efficient algorithm for CLSBM reduces misclassification rate.

Study how communication and feedback graphs affect learning outcomes.

We study distributed estimation methods under communication constraints in a distributed version of the nonparametric random design regression model. We derive minimax lower bounds and exhibit methods that attain those bounds. Moreover, we show that adaptive estimation is possible in this setting.

We study distributed optimization algorithms for minimizing the average of convex functions. The applications include empirical risk minimization problems in statistical machine learning where the datasets are large and have to be stored on different machines. We design a distributed stochastic variance reduced gradien…

The paper improves regret lower bounds for communicating MDPs.

In this paper, we consider the distributed stochastic multi-armed bandit problem, where a global arm set can be accessed by multiple players independently. The players are allowed to exchange their history of observations with each other at specific points in time. We study the relationship between regret and communica…

Paper proposes GPM for simultaneous community detection and group synchronization.

The study sets criteria for efficient communication in distributed online learning.

New framework for distributed nonparametric estimation under slow communication.

New algorithm reduces regret in collaborative multi-agent bandit problems.

We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared t…

The paper analyzes generalization of noisy iterative algorithms using communication theory.

A new test optimizes detecting small communities in large networks.

New uncertainty principle limits compression in distributed learning, suggesting optimal methods.

This paper studies the problem of nonparametric estimation of a smooth function with data distributed across multiple machines. We assume an independent sample from a white noise model is collected at each machine, and an estimator of the underlying true function needs to be constructed at a central machine. We place l…

Algorithm reduces regret in multi-agent bandits through gossiping.

A distributed algorithm reduces communication cost in linear bandits to near-optimal levels.

We study the following generalized matrix rank estimation problem: given an $n \times n$ matrix and a constant $c \geq 0$, estimate the number of eigenvalues that are greater than $c$. In the distributed setting, the matrix of interest is the sum of $m$ matrices held by separate machines. We show that any deterministic…

In this paper, we present two new communication-efficient methods for distributed minimization of an average of functions. The first algorithm is an inexact variant of the DANE algorithm that allows any local algorithm to return an approximate solution to a local subproblem. We show that such a strategy does not affect…

This study analyzes communication constraints in MoE architectures using information theory.

We consider the problem of estimating community memberships of nodes in a network, where every node is associated with a vector determining its degree of membership in each community. Existing provably consistent algorithms often require strong assumptions about the population, are computationally expensive, and only p…

Study shows more frequent communication in FL reduces model's generalization power.

This paper connects graph curvature to community structure.

Semidefinite programs have recently been developed for the problem of community detection, which may be viewed as a special case of the stochastic blockmodel. Here, we develop a semidefinite program that can be tailored to other instances of the blockmodel, such as non-assortative networks and overlapping communities. …

Paper proposes efficient weight updates for edge nodes with minimal communication.

New algorithm for weighted low rank approximation with provable guarantees.

This paper sets communication complexity bounds for distributed RL.

Optimizes learning policies in MDPs with weakly communicating structure.

New model for clustering dependent community Hawkes processes in temporal networks.

Online algorithm detects community structure in dynamic event streams.

Study on statistical estimation over Gaussian MAC, comparing analog and digital schemes.