YoVDO

Clipper - A Low-Latency Online Prediction Serving System

Offered By: USENIX via YouTube

Tags

USENIX Symposium on Networked Systems Design and Implementation (NSDI) Courses Machine Learning Courses System Architecture Courses

Course Description

Overview

Explore a conference talk on Clipper, a low-latency online prediction serving system designed to address the challenges of deploying machine learning models in real-time applications. Learn about Clipper's modular architecture that simplifies model deployment across various frameworks and applications. Discover how the system improves prediction latency, throughput, accuracy, and robustness through techniques like caching, batching, and adaptive model selection. Examine Clipper's performance on four machine learning benchmark datasets and its comparison to TensorFlow Serving. Gain insights into how Clipper enables model composition and online learning to enhance prediction accuracy and robustness without modifying underlying machine learning frameworks.

Syllabus

Introduction
Machine Learning
Prediction Serving
Oneoff Systems
Architecture
Experiments
Comparison to Tensorflow
Comparison to SIF
Model abstraction layer
Multiple models per application
Wrapup


Taught by

USENIX

Related Courses

SAP S/4HANA – Deep Dive
SAP Learning
Information Security- II
Indian Institute of Technology Madras via Swayam
Sistemas de gestión de la energía
Fundacion para la Eficiencia Energética via Independent
Базы данных (Databases)
Saint Petersburg State University via Coursera
Системное мышление
Moscow Institute of Physics and Technology via Coursera