Augmented Inverse Probability Weighting and the Double Robustness Property

This article discusses the augmented inverse propensity weighted (AIPW) estimator as an estimator for average treatment effects. The AIPW combines both the properties of the regression-based estimator and the inverse probability weighted (IPW) estimator and is therefore a “doubly robust” method in that it requires only either the propensity or outcome model to be correctly specified but not both. Even though this estimator has been known for years, it is rarely used in practice. After explaining the estimator and proving the double robustness property, I conduct a simulation study to compare the AIPW efficiency with IPW and regression under different scenarios of misspecification. In 2 real-world examples, I provide a step-by-step guide on implementing the AIPW estimator in practice. I show that it is an easily usable method that extends the IPW to reduce variability and improve estimation accuracy. [Box: see text]

Decision Tools Regarding Time Constraints Violation in Manufacturing Workshops

This paper is dedicated to the study of constraints violation in manufacturing workshops with time constraints. In such systems, every operation duration is included between minimal and maximal values. P-time Petri nets are used for modeling. A new theorem is introduced, constituting a decision tool about the occurrence of constraints violation at the level of a synchronization transition when various types of time disturbances occur. It shows the robustness properties of a manufacturing system on a range that may include delay and advance disturbances. The theoretical result is illustrated step by step on a given workshop. Two other lemmas are elaborated contributing to the study of the constraints violation problem. The final goal is to generalize the robustness property towards simultaneous occurrence of two delays at two points of the system, each having its own robustness range.

Improving Neural Network Verification through Spurious Region Guided Refinement

We propose a spurious region guided refinement approach for robustness verification of deep neural networks. Our method starts with applying the DeepPoly abstract domain to analyze the network. If the robustness property cannot be verified, the result is inconclusive. Due to the over-approximation, the computed region in the abstraction may be spurious in the sense that it does not contain any true counterexample. Our goal is to identify such spurious regions and use them to guide the abstraction refinement. The core idea is to make use of the obtained constraints of the abstraction to infer new bounds for the neurons. This is achieved by linear programming techniques. With the new bounds, we iteratively apply DeepPoly, aiming to eliminate spurious regions. We have implemented our approach in a prototypical tool DeepSRGR. Experimental results show that a large amount of regions can be identified as spurious, and as a result, the precision of DeepPoly can be significantly improved. As a side contribution, we show that our approach can be applied to verify quantitative robustness properties.

A study of supervised combined neural-network-based ultrasonic method for reconstruction of spatial distribution of material properties

This paper examines the performance of the commonly used neural-network-based classifiers for investigating a structural noise in metals as grain size estimation. The biggest problem which aims to identify the object structure grain size based on metal features or the object structure itself. When the structure data is obtained, a proposed feature extraction method is used to extract the feature of the object. Afterwards, the extracted features are used as the inputs for the classifiers. This research studies is focused to use basic ultrasonic sensors to obtain objects structural grain size which are used in neural network. The performance for used neural-network-based classifier is evaluated based on recognition accuracy for individual object. Also, traditional neural networks, namely convolutions and fully connected dense networks are shown as a result of grain size estimation model. To evaluate robustness property of neural networks, the original samples data is mixed for three types of grain sizes. Experimental results show that combined convolutions and fully connected dense neural networks with classifiers outperform the others single neural networks with original samples with high SN data. The Dense neural network as itself demonstrates the best robustness property when the object samples not differ from trained datasets.

Robustness of Surface Roughness against Low Number of Picture Elements and Its Benefit for Scaling Analysis

Surface roughness is widely used in the research of topography, and the scaling characteristics of roughness have been noticed in many fields. To rapidly obtain the relationship between root-mean-squared roughness (Rq) and measurement scale (L) could be helpful to achieve more understandings of the surface property, particularly the Rq-L curve could be fitted to calculate the fractal dimension (D). In this study, the robustness of Rq against low number of picture elements was investigated. Artificial surfaces and the surfaces of two actual samples (a silver thin film and a milled workpiece) were selected. When the number of picture elements was lowered, Rq was found to be stable within a large portion of the concerned scope. Such a robustness property could validate the feasibility of Rq-L curve obtained by segmenting a single morphological picture with roughness scaling extraction (RSE) method, which was proposed in our previous study. Since the traditional roughness (TR) method to obtain Rq-L curves was based on multiple pictures, which used a fixed number of picture elements at various L, RSE method could be significantly more rapid than TR method. Moreover, a direct comparison was carried out between RSE method and TR method in calculating the Rq-L curve and D, and the credibility and accuracy of RSE method with flatten order 1 and 2 was verified.

Multiply robust bootstrap variance estimation in the presence of singly imputed survey data

Item nonresponse in surveys is usually dealt with through single imputation. It is well known that treating the imputed values as if they were observed values may lead to serious underestimation of the variance of point estimators. In this article, we propose three pseudo-population bootstrap schemes for estimating the variance of imputed estimators obtained after applying a multiply robust imputation procedure. The proposed procedures can handle large sampling fractions and enjoy the multiple robustness property. Results from a simulation study suggest that the proposed methods perform well in terms of relative bias and coverage probability, for both population totals and quantiles.

Verifying Robustness of Gradient Boosted Models

Gradient boosted models are a fundamental machine learning technique. Robustness to small perturbations of the input is an important quality measure for machine learning models, but the literature lacks a method to prove the robustness of gradient boosted models.This work introduces VERIGB, a tool for quantifying the robustness of gradient boosted models. VERIGB encodes the model and the robustness property as an SMT formula, which enables state of the art verification tools to prove the model’s robustness. We extensively evaluate VERIGB on publicly available datasets and demonstrate a capability for verifying large models. Finally, we show that some model configurations tend to be inherently more robust than others.