Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
FlexiBO: A Decoupled Cost-Aware Multi-Objective...
Search
Pooyan Jamshidi
February 29, 2024
Science
0
100
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization of Deep Neural Networks
AAAI 2024
Pooyan Jamshidi
February 29, 2024
Tweet
Share
More Decks by Pooyan Jamshidi
See All by Pooyan Jamshidi
Reconciling Accuracy, Cost, and Latency of Inference Serving Systems
pjamshidi
0
120
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
pjamshidi
0
130
Learning from Valerie Issarny: Insights Gained from Program Co-Chairing SEAMS’23
pjamshidi
0
250
Artificial Intelligence and Systems Laboratory (AISys): A Research Overview
pjamshidi
0
560
Experiential Learning by Building Real-World AI Systems
pjamshidi
0
200
Understanding and Explaining the Root Causes of Performance Faults with Causal AI: A Path towards Building Dependable Computer Systems
pjamshidi
0
150
On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool Support
pjamshidi
0
240
Unicorn: Reasoning about Configurable System Performance through the Lens of Causality
pjamshidi
0
430
Causal AI for Systems
pjamshidi
0
290
Other Decks in Science
See All in Science
サイゼミ用因果推論
lw
1
2.9k
オンプレミス環境にKubernetesを構築する
koukimiura
0
110
いまAI組織が求める企画開発エンジニアとは?
roadroller
2
1.4k
インフラだけではない MLOps の話 @事例でわかるMLOps 機械学習の成果をスケールさせる処方箋 発売記念
icoxfog417
PRO
2
710
Planted Clique Conjectures are Equivalent
nobushimi
0
110
化学におけるAI・シミュレーション活用のトレンドと 汎用原子レベルシミュレーター: Matlantisを使った素材開発
matlantis
0
440
白金鉱業Meetup Vol.16_【初学者向け発表】 数理最適化のはじめの一歩 〜身近な問題で学ぶ最適化の面白さ〜
brainpadpr
10
2k
Improving Search @scale with efficient query experimentation @BerlinBuzzwords 2024
searchhub
0
270
創薬における機械学習技術について
kanojikajino
16
4.9k
非同期コミュニケーションの構造 -チャットツールを用いた組織における情報の流れの設計について-
koisono
0
210
All-in-One Bioinformatics Platform Realized with Snowflake ~ From In Silico Drug Discovery, Disease Variant Analysis, to Single-Cell RNA-seq
ktatsuya
0
300
03_草原和博_広島大学大学院人間社会科学研究科教授_デジタル_シティズンシップシティで_新たな_学び__をつくる.pdf
sip3ristex
0
120
Featured
See All Featured
The Invisible Side of Design
smashingmag
299
50k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
The Art of Programming - Codeland 2020
erikaheidi
53
13k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
366
25k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
4
350
Docker and Python
trallard
44
3.3k
Build The Right Thing And Hit Your Dates
maggiecrowley
34
2.5k
The Cult of Friendly URLs
andyhume
78
6.2k
Navigating Team Friction
lara
183
15k
A Modern Web Designer's Workflow
chriscoyier
693
190k
Designing for Performance
lara
604
68k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Transcript
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization of Deep Neural Networks
Shahriar Iqbal, Jianhai Su, Lars Kotthoff, Pooyan Jamshidi larsko@uwyo.edu AAAI, 24 February 2024 1
One Size Does Not Fit All 1 1.5 2 2.5
3 3.5 ·104 15 20 25 30 35 40 Energy Consumption (mJ) Prediction Error (%) Xception ← Energy consumption varies 4 × → ← Prediction Error varies 3 × → 2
Heterogeneous Parameters Num of Filters, Filter Size, Learning Rate, Num
of Epochs DN N Design Compiler Hardware Deployment Num of Active CPUs, CPU/ GPU/ EMC Frequency Cloud, IoT, Edge Num of Threads, GPU Threads, Memory Growth 3
Cost-Unaware Methods Waste Resources Coupled Unaware Pareto Optimal Prediction Error
(%) Log Wall Clock Time Energy Consumption (mJ) 3000 6000 9000 12000 15 25 35 45 3.65 3.50 3.35 Decoupled Aware Pareto Optimal Prediction Error (%) Log Wall Clock Time Energy Consumption (mJ) 3000 6000 9000 12000 15 25 35 45 3.65 3.50 3.35 4
Proposed Method ▷ weight expected benefit of evaluation by cost
▷ choose which objective(s) to evaluate ▷ more efficient use of resources – lower cost, more evaluations 5
Results – Computer Vision 0 50 100 150 200 Cumulative
Log WallClock Time 0.15 0.20 0.25 0.30 0.35 0.40 0.45 0.50 0.55 Hypervolume Error Xception PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 10000 15000 20000 25000 Energy Consumption (mJ) 15 20 25 30 35 40 Prediction Error (%) Xception PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 6
Results – NLP 0 50 100 150 200 Cumulative Log
WallClock Time 0.20 0.25 0.30 0.35 0.40 0.45 0.50 0.55 Hypervolume Error BERT-SQuAD PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 20000 30000 40000 50000 60000 70000 80000 90000 Energy Consumption (mJ) 20 25 30 35 Prediction Error (%) BERT-SQuAD PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 7
Results – Speech Recognition 0 50 100 150 200 250
300 Cumulative Log WallClock Time 0.25 0.30 0.35 0.40 0.45 0.50 0.55 Hypervolume Error DeepSpeech PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 20000 30000 40000 50000 60000 Energy Consumption (mJ) 17.5 20.0 22.5 25.0 27.5 30.0 32.5 35.0 Prediction Error (%) DeepSpeech PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 8
Results – Evaluations 0 20 40 60 80 100 120
140 160 180 200 PAL 0 20 40 60 80 100 120 140 160 180 200 PESMO-DEC 2 4 6 8 0 20 40 60 80 100 120 140 160 180 200 Iteration CA-MOBO 0 20 40 60 80 100 120 140 160 180 200 Iteration FlexiBO 2 4 6 8 9
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization of Deep Neural Networks
▷ cost-aware acquisition function decreases cost and improves results ▷ code available at https://github.com/softsys4ai/FlexiBO 0 50 100 150 200 250 300 Cumulative Log WallClock Time 0.25 0.30 0.35 0.40 0.45 0.50 0.55 Hypervolume Error DeepSpeech PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 20000 30000 40000 50000 60000 Energy Consumption (mJ) 17.5 20.0 22.5 25.0 27.5 30.0 32.5 35.0 Prediction Error (%) DeepSpeech PAL PESMO ParEGO SMSEGO CA-MOBO PESMO-DEC FLEXIBO-GPLC 10