neural networks for predicting algorithm runtime
play

Neural Networks for Predicting Algorithm Runtime Distributions - PowerPoint PPT Presentation

Jan 18, 2023 •301 likes •588 views

Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius Lindauer & Frank Hutter Paper ID #2772 Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 IJCAI2018 Motivation

  1. Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius Lindauer & Frank Hutter Paper ID #2772 Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 IJCAI’2018

  2. Motivation Algorithm portfolios yield state-of-the-art performance for SAT, ASP, Planning, … → to build these we can make use of runtime predictions Other applications: ● Optimal restarts ● Algorithm selection ● Algorithm configurations Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 2 IJCAI’2018

  3. Describing the Runtime of an Algorithm? solve(instance, seed): # do something return solution, runtime runtime Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 3 IJCAI’2018

  4. Describing the Runtime of an Algorithm? solve(instance, seed): # do something return solution, runtime runtime Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 3 IJCAI’2018

  5. Contributions 1 Study how to predict parametric RTDs 2 Propose DistNet , a practical neural network for predicting RTDs 3 Evaluate DistNet and show that it can learn from only a few samples per instance Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 4 IJCAI’2018

  6. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 5 IJCAI’2018

  7. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 5 IJCAI’2018

  8. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 5 IJCAI’2018

  9. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 5 IJCAI’2018

  10. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 6 IJCAI’2018

  11. Empirical RTDs Clasp-factoring LPG-Zenotravel SAPS-CV-VAR p(solved by this time) Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 7 IJCAI’2018

  12. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 8 IJCAI’2018

  13. Considered Parametric Distribution Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 9 IJCAI’2018

  14. Quantifying the Quality of Runtime Distributions (1) observed runtimes distribution parameter Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 10 IJCAI’2018

  15. Quantifying the Quality of Runtime Distributions (1) observed runtimes distribution parameter (2) Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 10 IJCAI’2018

  16. Typical Pipeline for Runtime prediction Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 11 IJCAI’2018

  17. Predicting multiple Runtime Distributions Option 1 For each training instance → fit the parametric distribution’s parameter on observed runtimes. Then for all training instances, for each distribution parameter: fit a model Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 12 IJCAI’2018

  18. Predicting multiple Runtime Distributions Option 1 For each training instance → fit the parametric distribution’s parameter on observed runtimes. Then for all training instances, for each distribution parameter: fit a model Problematic, because models ● can only be as good as each fitted distribution ● do not know about interaction between their outputs ● typically minimize loss in the parameter space Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 12 IJCAI’2018

  19. Predicting multiple Runtime Distributions Option 2 For each training instance → fit the parametric distribution’s parameter on observed runtimes. Then for all training instances, for each distribution parameter: fit a model with multiple outputs Problematic, because model ● can only be as good as each fitted distribution ● does not know about interaction between their outputs ● typically minimizes loss in the parameter space Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 12 IJCAI’2018

  20. Predicting multiple Runtime Distributions DistNet For each training instance → fit the parametric distribution’s parameter on observed runtimes. Then for all training instances, for each distribution parameter: fit a neural network using negative log-likelihood as a loss function Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 12 IJCAI’2018

  21. Results We compared ● DistNet ● independent Random Forests (iRF) ● multi-output Random Forests (mRF) on 7 scenarios from SAT solving and AI planning. [...] Table : Averaged negative log-likelihood achieved for predicting RTDs for Figure : Averaged negative log-likelihood. Smaller values are better. unseen instances Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 16 IJCAI’2018

  22. Results We compared ● DistNet ● independent Random Forests (iRF) ● multi-output Random Forests (mRF) on 7 scenarios from SAT solving and AI planning. [...] Table : Averaged negative log-likelihood achieved for predicting RTDs for Figure : Averaged negative log-likelihood. Smaller values are better. unseen instances Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 16 IJCAI’2018

  23. Results We compared ● DistNet ● independent Random Forests (iRF) ● multi-output Random Forests (mRF) on 7 scenarios from SAT solving and AI planning. [...] → Predicting parameters for RTDs is possible → Joint predictions work better → DistNet provides more robust predictions which are often better than those of Table : Averaged negative log-likelihood achieved for predicting RTDs for Figure : Averaged negative log-likelihood. Smaller values are better. unseen instances competitors Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 16 IJCAI’2018

  24. DistNet on a Low Number of Observations multi-ouput Random Forest averaged NLLH DistNet Distribution fitted on all samples Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 17 IJCAI’2018

  25. Wrap-Up We have proposed DistNet, which + jointly learns distribution parameters + directly optimizes the loss function of interest + performs well even if only few observations per instance are available Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 18 IJCAI’2018

  26. Wrap-Up We have proposed DistNet, which + jointly learns distribution parameters + directly optimizes the loss function of interest + performs well even if only few observations per instance are available Open Questions: - How to automatically determine a well fitting distribution family? - How to handle heterogeneous datasets? Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 18 IJCAI’2018

  27. Wrap-Up We have proposed DistNet, which + jointly learns distribution parameters + directly optimizes the loss function of interest + performs well even if only few observations per instance are available Open Questions: - How to automatically determine a well fitting distribution family? - How to handle heterogeneous datasets? Code and data: https://www.automl.org/distnet/ Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 18 IJCAI’2018

Recommend

Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology

Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology

Computational Algorithm Predicting Surface Computational Algorithm Predicting Surface Morphology Evolution During Electropolishing Joel Thomas 1 , Charles Reece 2 and Stanko R. Brankovic 1,* 1 Cullen College of Engineering University of Houston

399 views • 12 slides
How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . .

How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . .

Need for Machine . . . Neural Networks . . . How to Speed Up . . . Neural Networks: A . . . How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . . . Resulting Algorithm Faster by Taking Into How to

464 views • 17 slides
Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM

Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM Transactions on Graphics, Publication date: November 2017 Presenter: MinKu Kang In Previous Talk

911 views • 21 slides
Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 20), August 23 27, 2020, Virtual Event, CA, USA. Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

440 views • 18 slides
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov ICCV 2015 Presenter: Fartash Faghri Zero-shot Learning Classify images of an unseen class

156 views • 12 slides
DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks Fabien Geyer 1,2 and Steffen Bondorf 3 INFOCOM 2019 Wednesday 1 st May, 2019 1 Chair of Network Architectures and Services 3 Dept. of Information

711 views • 57 slides
A Self-Organizing Fuzzy Neural Networks H. S. LI N, X. Z. GAO, XI ANLI N HUANG, AND Z. Y. SONG

A Self-Organizing Fuzzy Neural Networks H. S. LI N, X. Z. GAO, XI ANLI N HUANG, AND Z. Y. SONG

A Self-Organizing Fuzzy Neural Networks H. S. LI N, X. Z. GAO, XI ANLI N HUANG, AND Z. Y. SONG Abstract This paper proposes a novel clustering algorithm for the structure learning of fuzzy neural networks. Our clustering algorithm uses

635 views • 37 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides
Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

852 views • 33 slides
Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

1.17k views • 91 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides
Neural Networks for Machine Learning Lecture 12a The Boltzmann Machine learning algorithm

Neural Networks for Machine Learning Lecture 12a The Boltzmann Machine learning algorithm

Neural Networks for Machine Learning Lecture 12a The Boltzmann Machine learning algorithm Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed The goal of learning We want to maximize the It is also

755 views • 47 slides
Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.57k views • 124 slides
Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.63k views • 119 slides
Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography

Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography

Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography Hopfield, J. J., "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the National Academy

367 views • 19 slides
Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training

Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training

Neural Networks and their Application to Go A. Bausch Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training neural networks Problems AlphaGo Anne-Marie Bausch The Game of Go Policy Network

280 views • 24 slides
(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning objectives What are neural networks? What are deep neural networks? How do we train neural networks? What variants of neural network

331 views • 31 slides
Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron. A look at some current works. Adding an evolutionary strategy. Paul Nuytten CPSC 607 Why Model Neural Networks? The Neuron The nervous

697 views • 4 slides
Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In

987 views • 40 slides
Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Learning in Neural Networks w 1,3 w 3,5 1 3 5 w w 1,4 3,6 w w 2,3 4,5 2 4 6 w w 2,4 4,6 Class #18: Back-Propagation; } A neural network can learn a classification function by Tuning Hyper-Parameters adjusting its weights to

259 views • 4 slides
Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What well cover ... f ( x ) computer vision architectures - convolutional networks - data augmentation 1 - residual networks ... ...

1.29k views • 75 slides
Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC

Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC

Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC www.kit.edu KIT The Research University in the Helmholtz Association Neural Network Concept (very) remotely brain inspired computational system

479 views • 25 slides
Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova November 21, 2016 Neural Networks 2/20 Neural Networks 3/20 Neural Networks Neural computing requires a number of neurons , to be connected

813 views • 21 slides
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation Marco Ancona , Cengiz ztireli 2 , Markus Gross 1,2 1 Department of Computer Science, ETH Zurich, Switzerland 2 Disney Research, Zurich, Switzerland

1.09k views • 41 slides

More recommend