scholarly journals Predict+Optimise with Ranking Objectives: Exhaustively Learning Linear Functions

2019 ◽  
Author(s):  
Emir Demirovic ◽  
Peter J. Stuckey ◽  
James Bailey ◽  
Jeffrey Chan ◽  
Christopher Leckie ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computational Complexity ◽  
Combinatorial Optimisation ◽  
Linear Functions ◽  
Optimal Parameters ◽  
Common Goal ◽  
Learning Function ◽  
Input Parameters ◽  
Theoretical Insight ◽  
Insight Into

We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. Our contributions are two-fold: 1) we provide theoretical insight into the properties and computational complexity of predict+optimise problems in general, and 2) develop a novel framework that, in contrast to related work, guarantees to compute the optimal parameters for a linear learning function given any ranking optimisation problem. We illustrate the applicability of our framework for the particular case of the unit-weighted knapsack predict+optimise problem and evaluate on benchmarks from the literature.

scholarly journals Dynamic Programming for Predict+Optimise

2020 ◽  
Vol 34 (02) ◽  
pp. 1444-1451
Author(s):  
Emir Demirovi? ◽  
Peter J. Stuckey ◽  
Tias Guns ◽  
James Bailey ◽  
Christopher Leckie ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dynamic Programming ◽  
Linear Function ◽  
Piecewise Linear ◽  
Combinatorial Problem ◽  
Piecewise Linear Function ◽  
Combinatorial Optimisation ◽  
Common Goal ◽  
Learning Functions ◽  
Learning Technique

We study the predict+optimise problem, where machine learning and combinatorial optimisation must interact to achieve a common goal. These problems are important when optimisation needs to be performed on input parameters that are not fully observed but must instead be estimated using machine learning. We provide a novel learning technique for predict+optimise to directly reason about the underlying combinatorial optimisation problem, offering a meaningful integration of machine learning and optimisation. This is done by representing the combinatorial problem as a piecewise linear function parameterised by the coefficients of the learning model and then iteratively performing coordinate descent on the learning coefficients. Our approach is applicable to linear learning functions and any optimisation problem solvable by dynamic programming. We illustrate the effectiveness of our approach on benchmarks from the literature.

scholarly journals Fast Linear Interpolation

2021 ◽  
Vol 17 (2) ◽  
pp. 1-15
Author(s):  
Nathan Zhang ◽  
Kevin Canini ◽  
Sean Silva ◽  
Maya Gupta
Keyword(s):  
Machine Learning ◽  
Piecewise Linear ◽  
Lattice Models ◽  
Function Class ◽  
Linear Interpolation ◽  
Linear Functions ◽  
Piecewise Linear Functions ◽  
Learning Function ◽  
Interpolation Operators ◽  
New Strategies

We present fast implementations of linear interpolation operators for piecewise linear functions and multi-dimensional look-up tables. These operators are common for efficient transformations in image processing and are the core operations needed for lattice models like deep lattice networks, a popular machine learning function class for interpretable, shape-constrained machine learning. We present new strategies for an efficient compiler-based solution using MLIR to accelerate linear interpolation. For real-world machine-learned multi-layer lattice models that use multidimensional linear interpolation, we show these strategies run 5-10× faster on a standard CPU compared to an optimized C++ interpreter implementation.

Theoretical insight into the CdS/FAPbI3 heterostructure: a promising visible-light absorber

2021 ◽  
Author(s):  
Junli Chang ◽  
Liping Jiang ◽  
Guangzhao Wang ◽  
Yuhong Huang ◽  
Hong Chen
Keyword(s):  
Optical Absorption ◽  
Visible Light ◽  
Visible Light Range ◽  
Light Absorber ◽  
Absorption Performance ◽  
Theoretical Insight ◽  
Insight Into

The optical absorption performance of the perovskite FAPbI3 in the visible-light range is significantly improved by constructing a CdS/FAPbI3 heterostructure.

scholarly journals Theoretical Insight into the Reversal of Chemoselectivity in Diels-Alder Reactions of α,β-Unsaturated Aldehydes and Ketones Catalyzed by Brønsted and Lewis Acids

Organics ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 38-49
Author(s):  
Lakhdar Benhamed ◽  
Sidi Mohamed Mekelleche ◽  
Wafaa Benchouk
Keyword(s):  
Lewis Acids ◽  
Major Product ◽  
Diels Alder ◽  
Unsaturated Ketone ◽  
Unsaturated Aldehydes ◽  
Aldehydes And Ketones ◽  
Theoretical Insight ◽  
Insight Into ◽  
Good Agreement

Experimentally, a reversal of chemoselectivity has been observed in catalyzed Diels–Alder reactions of α,β-unsaturated aldehydes (e.g., (2E)-but-2-enal) and ketones (e.g., 2-hexen-4-one) with cyclopentadiene. Indeed, using the triflimidic Brønsted acid Tf2NH as catalyst, the reaction gave a Diels–Alder adduct derived from α,β-unsaturated ketone as a major product. On the other hand, the use of tris(pentafluorophenyl)borane B(C6F5)3 bulky Lewis acid as catalyst gave mainly the cycloadduct of α,β-unsaturated aldehyde as a major product. Our aim in the present work is to put in evidence the role of the catalyst in the reversal of the chemoselectivity of the catalyzed Diels–Alder reactions of (2E)-but-2-enal and 2-Hexen-4-one with cyclopentadiene. The calculations were performed at the ωB97XD/6-311G(d,p) level of theory and the solvent effects of dichloromethane were taken into account using the PCM solvation model. The obtained results are in good agreement with experimental outcomes.

On the Complexity of Deadlock Recovery

1986 ◽  
Vol 9 (3) ◽  
pp. 323-342
Author(s):  
Joseph Y.-T. Leung ◽  
Burkhard Monien
Keyword(s):  
Computational Complexity ◽  
Polynomial Time ◽  
Arbitrary Number ◽  
The Other ◽  
Np Hard ◽  
Total Cost ◽  
Other Hand ◽  
Input Parameters ◽  
Resource Type

We consider the computational complexity of finding an optimal deadlock recovery. It is known that for an arbitrary number of resource types the problem is NP-hard even when the total cost of deadlocked jobs and the total number of resource units are “small” relative to the number of deadlocked jobs. It is also known that for one resource type the problem is NP-hard when the total cost of deadlocked jobs and the total number of resource units are “large” relative to the number of deadlocked jobs. In this paper we show that for one resource type the problem is solvable in polynomial time when the total cost of deadlocked jobs or the total number of resource units is “small” relative to the number of deadlocked jobs. For fixed m ⩾ 2 resource types, we show that the problem is solvable in polynomial time when the total number of resource units is “small” relative to the number of deadlocked jobs. On the other hand, when the total number of resource units is “large”, the problem becomes NP-hard even when the total cost of deadlocked jobs is “small” relative to the number of deadlocked jobs. The results in the paper, together with previous known ones, give a complete delineation of the complexity of this problem under various assumptions of the input parameters.

scholarly journals Ensemble Machine Learning Assisted Reservoir Characterization Using Field Production Data–An Offshore Field Case Study

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1052
Author(s):  
Baozhong Wang ◽  
Jyotsna Sharma ◽  
Jianhua Chen ◽  
Patricia Persaud
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Reservoir Characterization ◽  
Time Lapse ◽  
Production Data ◽  
Oil Saturation ◽  
Ensemble Machine Learning ◽  
Input Parameters ◽  
Saturation Profiles ◽  
Field Production

Estimation of fluid saturation is an important step in dynamic reservoir characterization. Machine learning techniques have been increasingly used in recent years for reservoir saturation prediction workflows. However, most of these studies require input parameters derived from cores, petrophysical logs, or seismic data, which may not always be readily available. Additionally, very few studies incorporate the production data, which is an important reflection of the dynamic reservoir properties and also typically the most frequently and reliably measured quantity throughout the life of a field. In this research, the random forest ensemble machine learning algorithm is implemented that uses the field-wide production and injection data (both measured at the surface) as the only input parameters to predict the time-lapse oil saturation profiles at well locations. The algorithm is optimized using feature selection based on feature importance score and Pearson correlation coefficient, in combination with geophysical domain-knowledge. The workflow is demonstrated using the actual field data from a structurally complex, heterogeneous, and heavily faulted offshore reservoir. The random forest model captures the trends from three and a half years of historical field production, injection, and simulated saturation data to predict future time-lapse oil saturation profiles at four deviated well locations with over 90% R-square, less than 6% Root Mean Square Error, and less than 7% Mean Absolute Percentage Error, in each case.

scholarly journals Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 930
Author(s):  
Fahimeh Hadavimoghaddam ◽  
Mehdi Ostadhassan ◽  
Ehsan Heidaryan ◽  
Mohammad Ali Sadri ◽  
Inna Chapanova ◽  
...  
Keyword(s):  
Machine Learning ◽  
Viscosity Data ◽  
Oil Viscosity ◽  
Pvt Data ◽  
Proposed Model ◽  
Wide Range ◽  
Engineering Problems ◽  
Functional Forms ◽  
Insight Into

Dead oil viscosity is a critical parameter to solve numerous reservoir engineering problems and one of the most unreliable properties to predict with classical black oil correlations. Determination of dead oil viscosity by experiments is expensive and time-consuming, which means developing an accurate and quick prediction model is required. This paper implements six machine learning models: random forest (RF), lightgbm, XGBoost, multilayer perceptron (MLP) neural network, stochastic real-valued (SRV) and SuperLearner to predict dead oil viscosity. More than 2000 pressure–volume–temperature (PVT) data were used for developing and testing these models. A huge range of viscosity data were used, from light intermediate to heavy oil. In this study, we give insight into the performance of different functional forms that have been used in the literature to formulate dead oil viscosity. The results show that the functional form f(γAPI,T), has the best performance, and additional correlating parameters might be unnecessary. Furthermore, SuperLearner outperformed other machine learning (ML) algorithms as well as common correlations that are based on the metric analysis. The SuperLearner model can potentially replace the empirical models for viscosity predictions on a wide range of viscosities (any oil type). Ultimately, the proposed model is capable of simulating the true physical trend of the dead oil viscosity with variations of oil API gravity, temperature and shear rate.

scholarly journals Insight into metastatic oral cancer tissue from novel analyses using FTIR spectroscopy and aperture IR-SNOM

The Analyst ◽  
2021 ◽  
Author(s):  
Barnaby Ellis ◽  
Conor A Whitley ◽  
Safaa Al Jedani ◽  
Caroline Smith ◽  
Philip Gunning ◽  
...  
Keyword(s):  
Machine Learning ◽  
Squamous Cell Carcinoma ◽  
Oral Cancer ◽  
Oral Squamous Cell Carcinoma ◽  
Lymphoid Tissue ◽  
Learning Algorithm ◽  
Cancer Tissue ◽  
Machine Learning Algorithm ◽  
Nodal Metastases ◽  
Insight Into

A novel machine learning algorithm is shown to accurately discriminate between oral squamous cell carcinoma (OSCC) nodal metastases and surrounding lymphoid tissue on the basis of a single metric, the...

An insight into predictive parameters of tablet capping by machine learning and multivariate tools

2021 ◽  
pp. 120439
Author(s):  
Shubhajit Paul ◽  
Yukteshwar Baranwal ◽  
Yin-Chao Tseng
Keyword(s):  
Machine Learning ◽  
Predictive Parameters ◽  
Insight Into
Sign in / Sign up

Export Citation Format

Share Document