Training time minimization for federated edge learning with optimized gradient quantization and bandwidth allocation

Training a machine learning model with federated edge learning(FEEL)is typically time consuming due to the constrained computation power of edge devices and the limited wireless resources in edge networks.In this study,the training time minimization problem is investigated in a quantized FEEL system,where heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels.In particular,a stochastic quantization scheme is adopted for compression of uploaded gradients,which can reduce the burden of per-round communication but may come at the cost of increasing the number of communication rounds.The training time is modeled by taking into account the communication time,computation time,and the number of communication rounds.Based on the proposed training time model,the intrinsic trade-off between the number of communication rounds and per-round latency is characterized.Specifically,we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap.Furthermore,a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap,based on which the closed-form expressions for the number of communication rounds and the total training time are obtained.Constrained by the total bandwidth,the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem.To this end,an algorithm based on alternating optimization is proposed,which alternatively solves the subproblem of quantization optimization through successive convex approximation and the subproblem of bandwidth allocation by bisection search.With different learning tasks and models,the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the simulation results.

Recognizing Early Warning Signs (EWS) in Patients Is Critically Important

Introduction: Monitoring vital signs is a basic indicator of a patient’s health status and allows prompt detection of delayed recovery or adverse effects and early intervention. Patients with adverse events during hospitalization often display clinical decline for several hours before the event is observed. Non-critical care Nurses’ inconsistent recognition and response to patient deterioration lead to an increase in the length of hospital stay, unexpected admissions to the ICU, and increased morbidity and mortality. Aim: The study aimed to assess the factors that facilitate or impede the detection of early warning signs among adult patients hospitalized in tertiary care settings. Training should be provided to improve nurses’ knowledge, practice and attitude toward early warning signs of deteriorating patients leading to enhanced clinical judgment, skills and decision-making in addressing alerts. Methodology: A literature search was carried out in various databases;these were Cumulative Index to Nursing and Allied Health Literature (CINHAL), Google Scholar, PubMed, Science Direct, and Sage. The search area was narrowed from 2017 to 2022. The keywords used were “prevalence” AND “unplanned ICU admission”, “the importance of early warning signs” “outcome failure in rescue” “patient deterioration, communication” “improvement in early detection” AND “patient outcome admission” AND “early warning signs” AND “Pakistan”. After the analysis process, around 33 articles that met the inclusion criteria and were most relevant to the scope and context of the current study were considered. Conclusion: Most of the studies had reviewed literature in a qualitative retrospective observational study, content analysis, mixed method, and quasi-experimental study. The literature review identified that long hours of shift, nurse staffing levels, missed vital signs, lack of nursing training and education, and communication impact nurses’ ability to recognize and respond to early warning signs.

Prolate and Oblate Shape Coexistence in ^188Pt

A standard in-beam y-spectroscopy experiment for ^188Pt is performed via the ^176yb（^18O, 6n） reaction at beam energies of 88 and 95 MeV, and the level scheme for ^188Pt is established. Prolate and oblate shape coexistence has been demonstrated to occur in ^188Pt by applying the projected shell model. The rotation Mignment of i13/2 neutrons drives the yrast sequence changing suddenly from prolate to oblate shape at angular momentum 1Oh, indicating likely a new type of shape phase transition along the yrast fine in ^188Pt.

Optimal Dependence of Performance and Efficiency of Collaborative Filtering on Random Stratified Subsampling

Dropping fractions of users or items judiciously can reduce the computational cost of Collaborative Filtering(CF)algorithms.The effect of this subsampling on the computing time and accuracy of CF is not fully understood,and clear guidelines for selecting optimal or even appropriate subsampling levels are not available.In this paper,we present a Density-based Random Stratified Subsampling using Clustering(DRSC)algorithm in which the desired Fraction of Users Dropped(FUD)and Fraction of Items Dropped(FID)are specified,and the overall density during subsampling is maintained.Subsequently,we develop simple models of the Training Time Improvement(TTI)and the Accuracy Loss(AL)as functions of FUD and FID,based on extensive simulations of seven standard CF algorithms as applied to various primary matrices from MovieLens,Yahoo Music Rating,and Amazon Automotive data.Simulations show that both TTI and a scaled AL are bi-linear in FID and FUD for all seven methods.The TTI linear regression of a CF method appears to be same for all datasets.Extensive simulations illustrate that TTI can be estimated reliably with FUD and FID only,but AL requires considering additional dataset characteristics.The derived models are then used to optimize the levels of subsampling addressing the tradeoff between TTI and AL.A simple sub-optimal approximation was found,in which the optimal AL is proportional to the optimal Training Time Reduction Factor(TTRF)for higher values of TTRF,and the optimal subsampling levels,like optimal FID/(1-FID),are proportional to the square root of TTRF.