arXiv subjects

Eric Sung

Publications and source records attributed to Eric Sung.

3 recordsLinked to original sources

arXiv2026

Load Testing for Machine Learning Model Serving Systems at Scale

Machine learning (ML) model serving has become a dominant consumer of GPU infrastructure, yet capacity planning in these systems remains largely ad hoc. Under-provisioning leads to service-level objective (SLO) violations and production incidents, while over-provisioning results in substantial resource waste. This paper presents \sys, an industrial load testing framework for ML serving systems that systematically estimates serving capacity through an adaptive, feedback-driven search strategy. The approach leverages real-time performance signals, incorporating dampening, spike tolerance, and convergence detection to efficiently identify maximum sustainable throughput under SLO constraints. We evaluate \sys through a longitudinal analysis of 14 industrial case studies spanning four ML architecture classes: recommendation, ranking, vision, and NLP. This study demonstrates that systematic load testing leads to substantial improvements in GPU resource efficiency and operational reliability. Prior to adopting \sys, a significant fraction of model launches were under-provisioned, resulting in recurring incidents; these issues were substantially reduced after deployment. Our results show that ML-specific design decisions are critical to accurate capacity estimation: workload calibration using recorded traffic reduces estimation error from approximately 30\% to 2--6\%, while proper warmup handling yields a 22.2\% improvement in accuracy. Further analysis reveals key factors influencing prediction error, including model size and co-location effects. This paper distills six lessons and derive architectural guidelines for ML load testing, offering actionable insights for building reliable and efficient ML serving systems.

cs.LG↗

arXiv2021

Electromechanical modeling of human ventricles with ischemic cardiomyopathy: numerical simulations in sinus rhythm and under arrhythmia

We developed a novel patient-specific computational model for the numerical simulation of ventricular electromechanics in patients with ischemic cardiomyopathy (ICM). This model reproduces the activity both in sinus rhythm (SR) and in ventricular tachycardia (VT). The presence of scars, grey zones and non-remodeled regions of the myocardium is accounted for by the introduction of a spatially heterogeneous coefficient in the 3D electromechanics model. This 3D electromechanics model is firstly coupled with a 2-element Windkessel afterload model to fit the pressure-volume (PV) loop of a patient-specific left ventricle (LV) with ICM in SR. Then, we employ the coupling with a 0D closed-loop circulation model to analyze a VT circuit over multiple heartbeats on the same LV. We highlight similarities and differences on the solutions obtained by the electrophysiology model and those of the electromechanics model, while considering different scenarios for the circulatory system. We observe that very different parametrizations of the circulation model induce the same hemodynamical considerations for the patient at hand. Specifically, we classify this VT as unstable. We conclude by stressing the importance of combining electrophysiological, mechanical and hemodynamical models to provide relevant clinical indicators in how arrhythmias evolve and can potentially lead to sudden cardiac death.

math.NA↗

arXiv2020

A Physiology-Driven Computational Model for Post-Cardiac Arrest Outcome Prediction

Patients resuscitated from cardiac arrest (CA) face a high risk of neurological disability and death, however pragmatic methods are lacking for accurate and reliable prognostication. The aim of this study was to build computational models to predict post-CA outcome by leveraging high-dimensional patient data available early after admission to the intensive care unit (ICU). We hypothesized that model performance could be enhanced by integrating physiological time series (PTS) data and by training machine learning (ML) classifiers. We compared three models integrating features extracted from the electronic health records (EHR) alone, features derived from PTS collected in the first 24hrs after ICU admission (PTS24), and models integrating PTS24 and EHR. Outcomes of interest were survival and neurological outcome at ICU discharge. Combined EHR-PTS24 models had higher discrimination (area under the receiver operating characteristic curve [AUC]) than models which used either EHR or PTS24 alone, for the prediction of survival (AUC 0.85, 0.80 and 0.68 respectively) and neurological outcome (0.87, 0.83 and 0.78). The best ML classifier achieved higher discrimination than the reference logistic regression model (APACHE III) for survival (AUC 0.85 vs 0.70) and neurological outcome prediction (AUC 0.87 vs 0.75). Feature analysis revealed previously unknown factors to be associated with post-CA recovery. Results attest to the effectiveness of ML models for post-CA predictive modeling and suggest that PTS recorded in very early phase after resuscitation encode short-term outcome probabilities.

cs.LG↗