Embedding Decision Trees and Random Forests in Constraint Programming

Bonfietti, Alessio; Lombardi, Michele; Milano, Michela

doi:10.1007/978-3-319-18008-3_6

Cited by 25 publications

(28 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our task would be to construct a low‐power mapping of resources to jobs, which would require some form of search‐based optimization. For instance, methods relying on constraint programming are already widely used for HPC scheduling and could be extended to take into account power and job length predictions . Evolutionary techniques could also be a possibility.…”

Section: Discussion and Applicationsmentioning

confidence: 99%

A data‐driven approach to modeling power consumption for a hybrid supercomputer

Sîrbu

Babaoğlu

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Power consumption of current High Performance Computing systems has to be reduced by at least one order of magnitude before they can be scaled up towards ExaFLOP performance. While we can expect novel hardware technologies and architectures to contribute towards this goal, significant advances have to come also from software technologies such as proactive and power‐aware scheduling, resource allocation, and fault‐tolerant computing. Development of these software technologies in turn relies heavily on our ability to model and accurately predict power consumption in large computing systems. In this paper, we present a data‐driven model of power consumption for a hybrid supercomputer (which held the top spot in the Green500 ranking in June 2013) that combines CPU, GPU, and MIC technologies to achieve high levels of energy efficiency. Our model takes as input workload characteristics—the number and location of resources that are used by each job at a certain time—and calculates a predicted power consumption at the system level. The model is application‐code‐agnostic and is based solely on a data‐driven predictive approach, where log data describing the past jobs in the system are employed to estimate future power consumption. For this, three different model components are developed and integrated. The first employs support vector regression to predict power usage for jobs before these are started. The second uses a simple heuristic to predict the length of jobs, again before they start. The two predictions are then combined to estimate power consumption due to the job at all computational elements in the system. The third component is a linear model that takes as input the power consumption at the computing units and predicts system‐wide power consumption. Our method achieves highly‐accurate predictions starting solely from workload information and user histories. The model can be applied to power‐aware scheduling and power capping: alternative workload dispatching configurations can be evaluated from a power perspective and more efficient ones can be selected. The methodology outlined here can be easily adapted to other HPC systems where the same types of log data are available.

show abstract

Section: Discussion and Applicationsmentioning

confidence: 99%

A data‐driven approach to modeling power consumption for a hybrid supercomputer

Sîrbu

Babaoğlu

2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the actual network maximum with the described input ranges is 1.515, meaning that our bound is quite loose. The cause of the lack of tightness is having allowed conflicting values for x 1 in (8) and (9). Unfortunately, avoiding this miscalculation is impossible as long as we reason on each neuron individually.…”

Section: A Global Constraint For Two-layer Feed-forward Annsmentioning

confidence: 96%

“…The employed optimization techniques are instead Constraint Programming (CP) and Local Search. For more details, the interested reader can refer to [2,3,9]. EML approaches based on MixedInteger Non-Linear Programming (MINLP) and SAT Modulo Theories (SMT) are currently under development.…”

Section: Introductionmentioning

confidence: 99%

A lagrangian propagator for artificial neural networks in constraint programming

Lombardi

Gualandi²

2015

Constraints

Self Cite

View full text Add to dashboard Cite

This paper discusses a new method to perform propagation over a (two-layer, feed-forward) Neural Network embedded in a Constraint Programming model. The method is meant to be employed in Empirical Model Learning, a technique designed to enable optimal decision making over systems that cannot be modeled via conventional declarative means. The key step in Empirical Model Learning is to embed a Machine Learning model into a combinatorial model. It has been showed that Neural Networks can be embedded in a Constraint Programming model by simply encoding each neuron as a global constraint, which is then propagated individually. Unfortunately, this decomposition approach may lead to weak bounds. To overcome such limitation, we propose a new network-level propagator based on a non-linear Lagrangian relaxation that is solved with a subgradient algorithm. The method proved capable of dramatically reducing the search tree size on a thermal-aware dispatching problem on multicore CPUs. The overhead for optimizing the Lagrangian multipliers is kept within a reasonable level via a few simple techniques. This paper is an extended version of [27], featuring an improved structure, a new filtering technique for the network inputs, a set of overhead reduction techniques, and a thorough experimentation.

show abstract

“…The CLASSACQ idea of learning constraints from a trained classifier is not new. It is known that decision trees can be transformed into constraint models [10,29,45], as can artificial neural networks [4,27,29]. Some neural networks can also be transformed to integer programs [15,37,40].…”

Section: Constraint Acquisition By Naive Bayes Classifiermentioning

confidence: 99%

Classifier-based constraint acquisition

Prestwich

Freuder

O’Sullivan

et al. 2021

Ann Math Artif Intell

View full text Add to dashboard Cite

Modeling a combinatorial problem is a hard and error-prone task requiring significant expertise. Constraint acquisition methods attempt to automate this process by learning constraints from examples of solutions and (usually) non-solutions. Active methods query an oracle while passive methods do not. We propose a known but not widely-used application of machine learning to constraint acquisition: training a classifier to discriminate between solutions and non-solutions, then deriving a constraint model from the trained classifier. We discuss a wide range of possible new acquisition methods with useful properties inherited from classifiers. We also show the potential of this approach using a Naive Bayes classifier, obtaining a new passive acquisition algorithm that is considerably faster than existing methods, scalable to large constraint sets, and robust under errors.

show abstract

Embedding Decision Trees and Random Forests in Constraint Programming

Cited by 25 publications

References 21 publications

A data‐driven approach to modeling power consumption for a hybrid supercomputer

A data‐driven approach to modeling power consumption for a hybrid supercomputer

A lagrangian propagator for artificial neural networks in constraint programming

Classifier-based constraint acquisition

Contact Info

Product

Resources

About