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
140
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
160
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
pjamshidi
0
170
Learning from Valerie Issarny: Insights Gained from Program Co-Chairing SEAMS’23
pjamshidi
0
330
Artificial Intelligence and Systems Laboratory (AISys): A Research Overview
pjamshidi
0
650
Experiential Learning by Building Real-World AI Systems
pjamshidi
0
220
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
270
Unicorn: Reasoning about Configurable System Performance through the Lens of Causality
pjamshidi
0
460
Causal AI for Systems
pjamshidi
0
310
Other Decks in Science
See All in Science
データベース11: 正規化(1/2) - 望ましくない関係スキーマ
trycycle
PRO
0
710
機械学習 - pandas入門
trycycle
PRO
0
280
機械学習 - DBSCAN
trycycle
PRO
0
930
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
880
データベース03: 関係データモデル
trycycle
PRO
1
130
統計学入門講座 第3回スライド
techmathproject
0
110
テンソル分解による糖尿病の組織特異的遺伝子発現の統合解析を用いた関連疾患の予測
tagtag
2
200
データマイニング - ノードの中心性
trycycle
PRO
0
190
機械学習 - 決定木からはじめる機械学習
trycycle
PRO
0
990
機械学習 - 授業概要
trycycle
PRO
0
210
How To Buy, Verified Venmo Accounts in 2025 This year
usaallshop68
2
150
02_西村訓弘_プログラムディレクター_人口減少を機にひらく未来社会.pdf
sip3ristex
0
510
Featured
See All Featured
BBQ
matthewcrist
89
9.7k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
138
34k
GitHub's CSS Performance
jonrohan
1031
460k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
Automating Front-end Workflow
addyosmani
1370
200k
Raft: Consensus for Rubyists
vanstee
140
7k
Why Our Code Smells
bkeepers
PRO
337
57k
Product Roadmaps are Hard
iamctodd
PRO
54
11k
How to train your dragon (web standard)
notwaldorf
96
6.1k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.8k
Bash Introduction
62gerente
613
210k
What's in a price? How to price your products and services
michaelherold
246
12k
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