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
150
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
180
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
pjamshidi
0
180
Learning from Valerie Issarny: Insights Gained from Program Co-Chairing SEAMS’23
pjamshidi
0
350
Artificial Intelligence and Systems Laboratory (AISys): A Research Overview
pjamshidi
0
690
Experiential Learning by Building Real-World AI Systems
pjamshidi
0
230
Understanding and Explaining the Root Causes of Performance Faults with Causal AI: A Path towards Building Dependable Computer Systems
pjamshidi
0
180
On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool Support
pjamshidi
0
280
Unicorn: Reasoning about Configurable System Performance through the Lens of Causality
pjamshidi
0
470
Causal AI for Systems
pjamshidi
0
320
Other Decks in Science
See All in Science
データマイニング - ウェブとグラフ
trycycle
PRO
0
180
AIによる科学の加速: 各領域での革新と共創の未来
masayamoriofficial
0
150
機械学習 - K-means & 階層的クラスタリング
trycycle
PRO
0
1.1k
機械学習 - SVM
trycycle
PRO
1
890
データベース15: ビッグデータ時代のデータベース
trycycle
PRO
0
360
機械学習 - K近傍法 & 機械学習のお作法
trycycle
PRO
0
1.2k
05_山中真也_室蘭工業大学大学院工学研究科教授_だてプロの挑戦.pdf
sip3ristex
0
650
アナログ計算機『計算尺』を愛でる Midosuji Tech #4/Analog Computing Device Slide Rule now and then
quiver
1
280
academist Prize 4期生 研究トーク延長戦!「美は世界を救う」っていうけど、どうやって?
jimpe_hitsuwari
0
170
統計的因果探索: 背景知識とデータにより因果仮説を探索する
sshimizu2006
4
1k
Cross-Media Technologies, Information Science and Human-Information Interaction
signer
PRO
3
31k
機械学習 - ニューラルネットワーク入門
trycycle
PRO
0
860
Featured
See All Featured
What's in a price? How to price your products and services
michaelherold
246
12k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
33
2.5k
Large-scale JavaScript Application Architecture
addyosmani
514
110k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.1k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
2.6k
Producing Creativity
orderedlist
PRO
347
40k
Code Review Best Practice
trishagee
72
19k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.7k
Become a Pro
speakerdeck
PRO
29
5.5k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
890
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.2k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
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