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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

10 results for “client-server”

Differentially-Private "Draw and Discard" Machine Learningcs.CR

A new privacy-preserving ML framework using random sampling.

problem Achieving differential privacy in client-distributed ML.

method Draw and Discard: random model sampling for scalability and privacy.

result Demonstrated improved model quality and privacy guarantees.

differential privacy machine learning client-server asynchronous communication Generalized Linear models

2018-07-11abs ↗pdf ↗

A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Servicecs.LG

Paper introduces privacy-preserving deep-learning service.

problem Privacy loss in deep-learning-as-a-service.

method Homomorphic Encryption tailored for CNNs.

result Effectiveness of proposed privacy-preserving architecture.

Homomorphic Encryption Deep Learning Privacy Distributed Architecture Convolutional Neural Networks

2020-03-30abs ↗pdf ↗

Overpredictive Signal Analytics in Federated Learning: Algorithms and Analysiseess.SP

New algorithms improve signal processing in federated learning.

problem Efficiently process distributed signal samples with privacy and communication constraints.

method Proposes overpredictive signal approximations using convex optimization.

result Quantifies tradeoffs between communication cost, sampling rate, and approximation error.

federated learning signal processing IoT distributed learning overpredictive approximation

2024-10-02abs ↗pdf ↗

Embarrassingly Parallel GFlowNetscs.LG

EP-GFlowNets parallelize GFlowNet training for large-scale Bayesian inference.

problem Prohibitive repeated evaluations of unnormalized distributions for large-scale posterior sampling.

method Divide-and-conquer approach with server learning from local models.

result EP-GFlowNets enable efficient parallel and federated Bayesian inference.

GFlowNets Bayesian inference parallel computing federated learning MCMC alternatives

2024-06-05abs ↗pdf ↗

Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcs.LG

Enhanced federated learning reduces communication costs and improves model accuracy.

problem Reducing communication costs in federated learning.

method Asynchronous model update and temporally weighted aggregation.

result The proposed algorithm outperforms baseline in terms of communication cost and model accuracy.

federated learning asynchronous temporal aggregation deep learning communication efficiency

2019-03-18abs ↗pdf ↗

Towards Uncertainty-Aware Federated Granger Causal Learningcs.LG

Federated Granger causality learns reliable interactions without sharing data.

problem Uncertainty in federated Granger causality estimates.

method Closed-form covariance recursions and spectral-radius-based convergence conditions.

result Uncertainty depends only on client data statistics and is independent of model parameters.

Federated Learning Granger Causality Uncertainty Quantification Causal Structure Learning Spectral Radius

2026-02-13abs ↗pdf ↗

Federated Multi-Task Learning under a Mixture of Distributionscs.LG

Federated MTL learns personalized models under mixed distributions.

problem Heterogeneity of local data distributions leads to poor global model performance.

method Proposes federated MTL under mixture of distributions, using penalized optimization and federated EM-like algorithms.

result Models with higher accuracy and fairness than state-of-the-art methods.

Federated Learning Multi-Task Learning Personalized Models Mixture Distributions Federated EM

2021-08-23abs ↗pdf ↗

Mining Personalized Climate Preferences for Assistant Drivingcs.LG

Paper proposes personalized climate control for driver comfort.

problem Limited research on in-vehicle climate control and driver preferences.

method IoT platform for data collection, machine learning for driver behavior recognition, and personalized preference recommendation.

result Prototype demonstrates effective and accurate climate control for driver comfort.

driver behavior climate control IoT machine learning personalized preferences

2020-06-16abs ↗pdf ↗

Particle Swarm Optimized Federated Learning For Industrial IoT and Smart City Servicescs.LG

PSO optimizes hyperparameters for edge ML models in FL.

problem Efficient local training and inference at edge devices.

method Particle Swarm Optimization (PSO) for hyperparameter tuning.

result PSO reduces the number of communication rounds by 2 orders of magnitude.

Federated Learning Edge Computing Hyperparameter Optimization PSO Machine Learning

2020-09-05abs ↗pdf ↗

Technological improvement rate estimates for all technologies: Use of patent data and an extended domain descriptionecon.GN

Estimates yearly improvement rates for nearly all technologies using US patent data.

problem Providing a comprehensive account of technological change rates.

method Mapping patents to technology domains, calculating average centrality, and estimating improvement rates.

result Variation in improvement rates from 1.9% to 228.8% per year, with software-based domains often the fastest.

technological change patent data improvement rates technology domains centrality

2020-04-29abs ↗pdf ↗