Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

2535067581,011 · Jun 202019922001200920182026
48 results for communication performance

ComEx protocol reduces communication costs in cooperative bandits.

problem Minimizing communication costs in cooperative bandits while maintaining optimal performance.
method Developed ComEx protocol to reduce communication from Θ(T)Θ(T) to O(logT)O(\log T) messages.
result Achieves state-of-the-art performance with significantly reduced communication cost.

Improved distributed learning with reduced communication costs.

problem Efficient communication in resource-constrained environments for distributed learning.
method Proposed a cost-effective partial communication protocol.
result Communication cost is reduced to O(logT)O(\log T), improving significantly on full communication.

Study shows market volatility affects optimal communication design for trading strategies.

problem Investigating how communication impacts trading strategy performance in multi-agent systems.
method 5-agent LLM-based trading systems across 450 experiments spanning 21 months, comparing 5 organizational structures.
result Communication improves performance but depends on market characteristics, with competitive conversation excelling in volatile tech stocks.

Rewiring GNNs to optimize community and feature alignment improves their performance.

problem Improving GNNs' performance by addressing over-squashing and generalization issues.
method Three rewiring strategies: ComMa, FeaSt, and ComFy, targeting community structure, node labels, and their alignment.
result Rewiring strategies enhance GNNs' performance by optimizing label-community alignment.

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

problem Real-world distributed decision-making with imperfect communication.
method Proposed decentralized algorithms for three communication scenarios: stochastic networks, random delays, and adversarially corrupted rewards.
result Achieved competitive performance and near-optimal guarantees on group regret.

IC3Net improves communication efficiency in multiagent tasks.

problem Efficient communication in multiagent tasks, especially in semi-cooperative and competitive settings.
method IC3Net uses a gating mechanism and individualized rewards to control continuous communication, improving scalability and performance.
result IC3Net yields improved performance and convergence rates compared to baselines as task scale increases.

GRADE models evolving graph dynamics by learning node and community representations.

problem Lack of tools to study temporal community dynamics in evolving graphs.
method GRADE is a probabilistic model that learns evolving node and community representations via a random walk prior and variational inference.
result GRADE outperforms baselines in dynamic link prediction and dynamic community detection.

Study improves communication efficiency in RIS-assisted downlink communication.

problem Improving performance of RIS-aided downlink communication over heterogeneous designs.
method Distributed learning with distributionally robust optimization.
result Our algorithm achieves 50% fewer communication rounds for similar worst-case performance.

New communication topologies improve deep reinforcement learning performance.

problem Improving performance of learning agents in distributed reinforcement learning.
method Examined four graph families for communication topologies and found Erdos-Renyi random graphs to outperform fully connected topologies.
result Erdos-Renyi random graphs can improve performance of distributed learning agents.

A new method reduces communication in distributed RL without sacrificing performance.

problem High communication overhead in distributed RL systems.
method Adaptive policy gradient approach that skips communication during iterations.
result Reduces communication rounds needed for learning accuracy without degrading performance.

LASG improves communication efficiency in distributed learning.

problem Efficiently communicating gradients in distributed machine learning.
method Develops a new stochastic gradient descent approach, LASG, that predicts and selects significant communication rounds.
result Achieves communication savings by an order of magnitude in federated learning.

Event-triggered learning reduces communication in networked control systems.

problem Reduction of communication in networked control systems.
method Triggered learning experiments when communication performance is poor, using statistical properties of inter-communication times.
result Event-triggered learning improves robustness and communication efficiency.

HybridSGD improves SGD performance by balancing computation and communication.

problem Limited scalability and performance of SGD due to communication costs.
method 2D parallel SGD method (HybridSGD) that trades off between 1D ss-step SGD and 1D Federated SGD (FedAvg).
result HybridSGD achieves better convergence than FedAvg at similar processor scales and up to 121x speedup over FedAvg.

Paper proposes MLPCD for protein community detection in large PPI networks.

problem Identifying reliable protein communities from large-scale PPI networks.
method Integrates Gene Expression Data and uses Multi-source Learning with cloud computing.
result Demonstrates superior performance compared to existing methods.

Optimized parallel algorithms for identifying strong ties in data.

problem Identifying strong ties in data with varying distances and community sizes.
method Design and analysis of sequential and parallel algorithms for partitioned local depths.
result Optimized algorithms achieve up to 19.4x speedup in parallel execution.

The paper analyzes and improves the learning rates of distributed kernel ridge regression.

problem Generalization performance and learning rates of distributed kernel ridge regression.
method The paper derives optimal learning rates for DKRR in expectation and probability, proposes a communication strategy to improve learning performance, and evaluates these through theory and experiments.
result The communication strategy significantly improves the learning performance of DKRR, as demonstrated by both theoretical assessments and numerical experiments.

TarMAC targets and coordinates multi-agent communication for cooperative tasks.

problem Coordinating multi-agent reinforcement learning in partially observable environments.
method Targeted multi-round communication approach without supervision.
result Improved performance and sample efficiency in diverse environments.

DOSFL reduces federated learning communication by one round, preserving model performance.

problem High communication costs in federated learning with poorly distributed data.
method Clients distill their private data into synthetic data, sending only this to the server for training.
result Total communication cost up to 3 orders of magnitude less than FedAvg while maintaining comparable performance.

In this article, we study spectral methods for community detection based on α α-parametrized normalized modularity matrix hereafter called Lα {\bf L}_α in heterogeneous graph models. We show, in a regime where community detection is not asymptotically trivial, that Lα {\bf L}_α can be well approximated by a more tract…

2016-11-03abs ↗pdf ↗

Sketched SGD reduces communication in distributed SGD by sketching gradients.

problem Limited communication in large-scale distributed training of neural networks.
method Introducing Sketched SGD, an algorithm that communicates sketches of gradients instead of full gradients.
result Sketched SGD reduces communication from O(d)\mathcal{O}(d) or O(W)\mathcal{O}(W) to O(logd)\mathcal{O}(\log d), achieving up to 40x reduction in total communication cost.

This paper improves hierarchical community detection efficiency using local structural properties.

problem Efficiency of hierarchical community detection methods in large networks.
method Use of local structural network properties as proxies to improve efficiency.
result Achieves competitive results in modularity with improved efficiency.

Paper proposes double quantization to reduce communication in distributed machine learning.

problem High communication overhead in synchronizing stochastic gradients and model parameters in distributed training.
method Proposes double quantization for model parameters and gradients, and three communication-efficient algorithms.
result Established performance guarantees and demonstrated effective bit reduction without performance degradation.

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…

2013-09-01abs ↗pdf ↗

Efficient decentralized deep learning protocol reduces communication by orders of magnitude.

problem Training deep neural networks from distributed data sources with reduced communication.
method Dynamic model averaging protocol that handles different phases of model training and adapts to concept drifts.
result Reduction in communication by an order of magnitude compared to state-of-the-art approaches.

Deep learning optimizes vehicular communication zones for efficient data dissemination.

problem Overdimensioning and inefficient communication in vehicular floating content.
method Deep learning is used to select optimal broadcasting areas (Anchor Zones) for efficient message dissemination.
result The proposed method achieves an accuracy of 89.7% in predicting optimal Anchor Zones, saving up to 27% of resources.

A framework for multi-agent learning improves coordination through a memory-driven communication protocol.

problem Coordination and synchronisation in multi-agent systems with limited observations.
method A memory-driven communication protocol learned concurrently with individual policies during training.
result Superior performance in small-scale systems with up to six agents, demonstrating improved coordination.

Community detection is a central problem of network data analysis. Given a network, the goal of community detection is to partition the network nodes into a small number of clusters, which could often help reveal interesting structures. The present paper studies community detection in Degree-Corrected Block Models (DCB…

2016-07-24abs ↗pdf ↗

AITuning uses reinforcement learning to optimize communication libraries.

problem Optimizing communication libraries for better performance in parallel applications.
method Deep reinforcement learning applied to tuning communication libraries.
result Demonstrates the effectiveness of reinforcement learning for tuning communication libraries.

New model detects communities in multiplex networks, accounting for layer dependencies.

problem Detecting communities in multiplex networks with layer-specific dependencies.
method Hierarchical Bayesian model with a hierarchical Dirichlet prior and slice sampler.
result Model automatically picks the number of communities at each layer, outperforming single-layer alternatives.

Paper proposes SCALLION and SCAFCOM for compressed FL with reduced communication.

problem Reducing communication overhead in Federated Learning with data heterogeneity and partial participation.
method Revisit and simplify stochastic controlled averaging, proposing SCALLION and SCAFCOM for unbiased and biased compression.
result SCALLION and SCAFCOM outperform existing methods in communication and computation complexities.

A new gradient quantization scheme improves communication efficiency in distributed training.

problem Efficiently compressing gradients for parallel training of large models.
method Proposes a new gradient quantization scheme with theoretical guarantees and empirical performance.
result The new scheme matches and exceeds the performance of existing methods.

Efficient communication improves MARL performance in StarCraft II.

problem Achieving efficient communication among agents in multi-agent reinforcement learning.
method Variance Based Control (VBC) to limit message variance and preserve useful information.
result VBC reduces communication overhead by 2-10 times compared to state-of-the-art MARL algorithms.

Unified framework improves spectral graph clustering with generative community models.

problem Combining model-based and model-free approaches for robust community detection.
method SGC-GEN: Combines SGC with GENerative community models for theoretical and practical improvements.
result SGC-GEN provides theoretical guarantees and superior performance in community detection.