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
110
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
240
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
Analysis-Ready Cloud-Optimized Data for your community and the entire world with Pangeo-Forge
jbusecke
0
130
いまAI組織が求める企画開発エンジニアとは?
roadroller
2
1.4k
論文紹介: PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models (WSDM 2024)
ynakano
0
200
白金鉱業Meetup Vol.15 DMLによる条件付処置効果の推定_sotaroIZUMI_20240919
brainpadpr
2
670
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
100
大規模言語モデルの開発
chokkan
PRO
85
42k
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
700
(Forkwell Library #48)『詳解 インシデントレスポンス』で学び倒すブルーチーム技術
scientia
2
1.5k
WCS-LA-2024
lcolladotor
0
170
山形とさくらんぼに関するレクチャー(YG-900)
07jp27
1
260
マテリアルズ・インフォマティクスの先端で起きていること / What's Happening at the Cutting Edge of Materials Informatics
snhryt
1
170
All-in-One Bioinformatics Platform Realized with Snowflake ~ From In Silico Drug Discovery, Disease Variant Analysis, to Single-Cell RNA-seq
ktatsuya
PRO
0
290
Featured
See All Featured
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
33
2k
Building Your Own Lightsaber
phodgson
104
6.2k
A designer walks into a library…
pauljervisheath
205
24k
How GitHub (no longer) Works
holman
313
140k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
Building Adaptive Systems
keathley
39
2.4k
Intergalactic Javascript Robots from Outer Space
tanoku
270
27k
The World Runs on Bad Software
bkeepers
PRO
67
11k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
YesSQL, Process and Tooling at Scale
rocio
171
14k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
49
2.2k
Git: the NoSQL Database
bkeepers
PRO
427
64k
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