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
学術講演会中央大学学員会府中支部
tagtag
0
280
Quelles valorisations des logiciels vers le monde socio-économique dans un contexte de Science Ouverte ?
bluehats
1
420
オンプレミス環境にKubernetesを構築する
koukimiura
0
280
Lean4による汎化誤差評価の形式化
milano0017
1
260
統計学入門講座 第4回スライド
techmathproject
0
150
Ignite の1年間の軌跡
ktombow
0
130
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
880
Accelerated Computing for Climate forecast
inureyes
PRO
0
110
統計学入門講座 第3回スライド
techmathproject
0
110
Factorized Diffusion: Perceptual Illusions by Noise Decomposition
tomoaki0705
0
400
研究って何だっけ / What is Research?
ks91
PRO
1
100
Trend Classification of InSAR Displacement Time Series Using SAE–CNN
satai
3
480
Featured
See All Featured
BBQ
matthewcrist
89
9.7k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
21
1.3k
Being A Developer After 40
akosma
90
590k
A better future with KSS
kneath
238
17k
Reflections from 52 weeks, 52 projects
jeffersonlam
351
21k
How GitHub (no longer) Works
holman
314
140k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
Building Applications with DynamoDB
mza
95
6.5k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
How to Ace a Technical Interview
jacobian
278
23k
Optimizing for Happiness
mojombo
379
70k
Java REST API Framework Comparison - PWX 2021
mraible
31
8.7k
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