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
110
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
130
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
pjamshidi
0
140
Learning from Valerie Issarny: Insights Gained from Program Co-Chairing SEAMS’23
pjamshidi
0
270
Artificial Intelligence and Systems Laboratory (AISys): A Research Overview
pjamshidi
0
580
Experiential Learning by Building Real-World AI Systems
pjamshidi
0
210
Understanding and Explaining the Root Causes of Performance Faults with Causal AI: A Path towards Building Dependable Computer Systems
pjamshidi
0
160
On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool Support
pjamshidi
0
250
Unicorn: Reasoning about Configurable System Performance through the Lens of Causality
pjamshidi
0
440
Causal AI for Systems
pjamshidi
0
300
Other Decks in Science
See All in Science
多次元展開法を用いた 多値バイクラスタリング モデルの提案
kosugitti
0
280
小杉考司(専修大学)
kosugitti
2
630
Planted Clique Conjectures are Equivalent
nobushimi
0
130
応用心理学Ⅰテキストマイニング講義資料講義編(2024年度)
satocos135
0
120
LIMEを用いた判断根拠の可視化
kentaitakura
0
480
重複排除・高速バックアップ・ランサムウェア対策 三拍子そろったExaGrid × Veeam連携セミナー
climbteam
0
220
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
240
点群ライブラリPDALをGoogleColabにて実行する方法の紹介
kentaitakura
0
110
Improving Search @scale with efficient query experimentation @BerlinBuzzwords 2024
searchhub
0
280
機械学習を支える連続最適化
nearme_tech
PRO
1
300
[第62回 CV勉強会@関東] Long-CLIP: Unlocking the Long-Text Capability of CLIP / kantoCV 62th ECCV 2024
lychee1223
1
890
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
230
Featured
See All Featured
How to Think Like a Performance Engineer
csswizardry
22
1.5k
How to train your dragon (web standard)
notwaldorf
91
5.9k
Producing Creativity
orderedlist
PRO
344
40k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
46
2.4k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
YesSQL, Process and Tooling at Scale
rocio
172
14k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
Designing for Performance
lara
606
69k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
135
33k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
31
4.7k
Reflections from 52 weeks, 52 projects
jeffersonlam
349
20k
Docker and Python
trallard
44
3.3k
Transcript
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization of Deep Neural Networks
Shahriar Iqbal, Jianhai Su, Lars Kotthoff, Pooyan Jamshidi
[email protected]
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