arXiv research

A framework for multi-agent communication over noisy channels in reinforcement learning.

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

A new SBM for bipartite networks improves community detection in noisy data.

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 present a principled framework to address resource allocation for realizing boosting algorithms on substrates with communication or computation noise. Boosting classifiers (e.g., AdaBoost) make a final decision via a weighted vote from the outputs of many base classifiers (weak classifiers). Suppose that the base cl…

Two new coding schemes improve the efficient communication of noisy data.

Algorithm optimizes multi-player learning with noisy rewards without direct communication.

Study exact community recovery in noisy SBM with limited queries.

Paper studies signal detection in noisy environments with limited communication.

We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource limited communication between agents, and develops novel PAC guarantees in this…

The paper applies communication theory to improve language model reranking.

Paper tackles federated linear bandit learning with AirComp for noisy channels.

New techniques improve channel prediction in noisy wireless systems.

This paper employs the extrinsic information transfer (EXIT) method, a technique imported from the analysis of the iterative decoding of error control codes, to study the performance of belief propagation in community detection in the presence of side information. We consider both the detection of a single (hidden) com…

Paper improves robust spectral clustering for noisy data.

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are al…

In this note, we introduce a new algorithm to deal with finite dimensional clustering with errors in variables. The design of this algorithm is based on recent theoretical advances (see Loustau (2013a,b)) in statistical learning with errors in variables. As the previous mentioned papers, the algorithm mixes different t…

Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of cl…

Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications. However, achieving efficient communication among agents has always been an overarching problem in MARL. In this work, we propose Variance Based Control (VBC), a sim…

This paper considers a new framework to detect communities in a graph from the observation of signals at its nodes. We model the observed signals as noisy outputs of an unknown network process, represented as a graph filter that is excited by a set of unknown low-rank inputs/excitations. Application scenarios of this m…

Efficient algorithm detects communities in noisy graphs with robustness.

Noisy Pooled PCR tests large groups more efficiently.

A framework infers hyperedges and overlapping communities in hypergraphs.

Estimates curvature of network manifolds to understand community structure.

Study community detection in multi-view data with various types of information.

Paper uses SDP for community detection with side information.

Improved analysis of accelerated noisy power method for PCA.

Bayesian topological learning improves EEG signal analysis for brain state classification.

New algorithms reduce communication for sparse mean estimation in noisy distributed systems.

We consider learning of fundamental properties of communities in large noisy networks, in the prototypical situation where the nodes or users are split into two classes according to a binary property, e.g., according to their opinions or preferences on a topic. For learning these properties, we propose a nonparametric,…

Recent research on network embedding in hyperbolic space have proven successful in several applications. However, nodes in real world networks tend to interact through several distinct channels. Simple aggregation or ignorance of this multiplexity will lead to misleading results. On the other hand, there exists redunda…

Novel model detects communities in noisy multilayer networks.

We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighte…

FSGLD improves federated data sampling by correcting noisy gradients.

Private anchors affect how information is communicated and can improve or distort transmission.

New method improves convergence and reduces variance in noisy optimization problems.

The possibility of latency arbitrage in financial markets has led to the deployment of high-speed communication links between distant financial centers. These links are noisy and so there is a need for coding. In this paper, we develop a gametheoretic model of trading behavior where two traders compete to capture laten…

We consider the noisy power method algorithm, which has wide applications in machine learning and statistics, especially those related to principal component analysis (PCA) under resource (communication, memory or privacy) constraints. Existing analysis of the noisy power method shows an unsatisfactory dependency over …

Proposes a method for coarse graph alignment using sparse partial least squares.

Machine learning, and more specifically deep learning, have shown remarkable performance in sensing, communications, and inference. In this paper, we consider the application of the deep unfolding technique in the problem of signal reconstruction from its one-bit noisy measurements. Namely, we propose a model-based mac…

With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words re…

Unified sign-based compression for federated learning with faster convergence.

Study quantile reward identification with 1-bit feedback constraints.

Algorithm ensures fair information spread in social networks with community structure.

Market inefficiencies arise from density-dependent returns in a noisy environment.

Study neural communication systems with bandwidth-limited channels.

Federated learning for combinatorial multi-agent bandits reduces regret and speeds up with fewer communications.

Bayesian methods detect clusters in noisy data more reliably.