arXiv research

New algorithm reduces sample and communication complexities in federated Q-learning.

Community detection improves stock market portfolio optimization.

Study hypothesis testing under quantized samples with communication constraints, achieving near-optimal sample complexity.

SCAFFLSA reduces communication complexity for federated learning with heterogeneous clients.

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…

Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.

STL-SGD accelerates Local SGD by gradually increasing communication periods.

A new hybrid-ordered SGD method reduces communication and complexity for non-convex optimization.

New algorithms reduce communication costs in collaborative learning.

VRL-SGD reduces communication complexity in non-identical data settings.

A2SGD reduces distributed SGD communication to O(1) per worker.

Paper tackles low sample and communication complexities in decentralized bilevel optimization.

Efficiently addresses federated learning challenges with reduced communication and sample complexity.

With the help of transfer entropy, we analyze information flows between communities of complex networks. We show that the transfer entropy provides a coherent description of interactions between communities, including non-linear interactions. To put some flesh on the bare bones, we analyze transfer entropies between co…

Discovering community structure in complex networks is a mature field since a tremendous number of community detection methods have been introduced in the literature. Nevertheless, it is still very challenging for practioners to determine which method would be suitable to get insights into the structural information of…

New algorithm reduces FL sample and communication costs.

With the recent advances in complex networks theory, graph-based techniques for image segmentation has attracted great attention recently. In order to segment the image into meaningful connected components, this paper proposes an image segmentation general framework using complex networks based community detection algo…

We study the problem of identifying correlations in multivariate data, under information constraints: Either on the amount of memory that can be used by the algorithm, or the amount of communication when the data is distributed across several machines. We prove a tight trade-off between the memory/communication complex…

To solve the big topic modeling problem, we need to reduce both time and space complexities of batch latent Dirichlet allocation (LDA) algorithms. Although parallel LDA algorithms on the multi-processor architecture have low time and space complexities, their communication costs among processors often scale linearly wi…

ABCD model generates synthetic graphs for community detection with improved scalability and interpretability.

GradSkip reduces local training steps for better communication efficiency.

We study distribution testing with communication and memory constraints in the following computational models: (1) The {\em one-pass streaming model} where the goal is to minimize the sample complexity of the protocol subject to a memory constraint, and (2) A {\em distributed model} where the data samples reside at mul…

Federated learning supports exact support recovery with minimal communication.

Community detection in graphs has been extensively studied both in theory and in applications. However, detecting communities in hypergraphs is more challenging. In this paper, we propose a tensor decomposition approach for guaranteed learning of communities in a special class of hypergraphs modeling social tagging sys…

Statistical estimates can often be improved by fusion of data from several different sources. One example is so-called ensemble methods which have been successfully applied in areas such as machine learning for classification and clustering. In this paper, we present an ensemble method to improve community detection by…

This work improves Q-learning for average-reward MDPs, reducing sample and communication complexities in federated settings.

Multiplex networks have become increasingly more prevalent in many fields, and have emerged as a powerful tool for modeling the complexity of real networks. There is a critical need for developing inference models for multiplex networks that can take into account potential dependencies across different layers, particul…

One-layer transformers can't solve induction heads task efficiently.

New optimization for federated learning with local models.

New algorithm for weighted low rank approximation with provable guarantees.

Graphs help agents learn emergent communication.

New protocol reduces communication costs for heterogeneous bandits over complex networks.

Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…

Improved algorithm reduces communication rounds for distributed online learning.

DESTRESS optimizes decentralized nonconvex optimization with optimal IFO complexity and efficient communication.

Study binary hypothesis testing with privacy and communication constraints.

We present new algorithms for detecting the emergence of a community in large networks from sequential observations. The networks are modeled using Erdos-Renyi random graphs with edges forming between nodes in the community with higher probability. Based on statistical changepoint detection methodology, we develop thre…

A new model detects complex network communities using node attributes.

A new method for distributed optimization reduces communication rounds without minibatches.

The detection of community structure in stock market is of theoretical and practical significance for the study of financial dynamics and portfolio risk estimation. We here study the community structures in Chinese stock markets from the aspects of both price returns and turnover rates, by using a combination of the PM…

Affinity propagation is one of the most effective unsupervised pattern recognition algorithms for data clustering in high-dimensional feature space. However, the numerous attempts to test its performance for community detection in complex networks have been attaining results very far from the state of the art methods s…

A new approach for cooperative multi-agent reinforcement learning with limited communication, reducing the number of communication rounds.

This paper sets communication complexity bounds for distributed RL.

This paper provides new algorithms for distributed clustering for two popular center-based objectives, k-median and k-means. These algorithms have provable guarantees and improve communication complexity over existing approaches. Following a classic approach in clustering by \cite{har2004coresets}, we reduce the proble…

Analyzes methods for detecting communities in networks.

Optimizes learning policies in MDPs with weakly communicating structure.

This paper combines three techniques to reduce communications in distributed variational inequalities.

In distributed optimization and machine learning, multiple nodes coordinate to solve large problems. To do this, the nodes need to compress important algorithm information to bits so that it can be communicated over a digital channel. The communication time of these algorithms follows a complex interplay between a) the…