Owing to their inherently interpretable structure, decision trees are commonly used in applications where interpretability is essential. Recent work has focused on improving various aspects of decision trees, including their predictive power and robustness; however, their instability, albeit well-documented, has been addressed to a lesser extent. In this paper, we take a step towards the stabilization of decision tree models through the lens of real-world health care applications due to the relevance of stability and interpretability in this space. We introduce a new distance metric for decision trees and use it to determine a tree's level of stability. We propose a novel methodology to train stable decision trees and investigate the existence of trade-offs that are inherent to decision tree models - including between stability, predictive power, and interpretability. We demonstrate the value of the proposed methodology through an extensive quantitative and qualitative analysis of six case studies from real-world health care applications, and we show that, on average, with a small 4.6% decrease in predictive power, we gain a significant 38% improvement in the model's stability.

In recent years, numerous screening methods have been published for ultrahigh-dimensional data that contain hundreds of thousands of features; however, most of these features cannot handle data with thousands of classes. Prediction models built to authenticate users based on multichannel biometric data result in this type of problem. In this study, we present a novel method known as random forest-based multiround screening (RFMS) that can be effectively applied under such circumstances. The proposed algorithm divides the feature space into small subsets and executes a series of partial model builds. These partial models are used to implement tournament-based sorting and the selection of features based on their importance. To benchmark RFMS, a synthetic biometric feature space generator known as BiometricBlender is employed. Based on the results, the RFMS is on par with industry-standard feature screening methods while simultaneously possessing many advantages over these methods.

Laser-plasma physics has developed rapidly over the past few decades as high-power lasers have become both increasingly powerful and more widely available. Early experimental and numerical research in this field was restricted to single-shot experiments with limited parameter exploration. However, recent technological improvements make it possible to gather an increasing amount of data, both in experiments and simulations. This has sparked interest in using advanced techniques from mathematics, statistics and computer science to deal with, and benefit from, big data. At the same time, sophisticated modeling techniques also provide new ways for researchers to effectively deal with situations in which still only sparse amounts of data are available. This paper aims to present an overview of relevant machine learning methods with focus on applicability to laser-plasma physics, including its important sub-fields of laser-plasma acceleration and inertial confinement fusion.

Currently, the United States healthcare system has a "cruel tendency to delay or deny high-quality care to those who are most in need of it but can least afford its high cost," (Shmerling) resulting in rampant disparities in health outcomes throughout the nation. The news of today is riddled with stories of people receiving poor care due to systematic biases present in the modern healthcare system and the effect of the increasingly unaffordable cost of life-saving medication. In order to better understand the degree to which this inequality exists, we investigated which socioeconomic indicators model health outcomes best.

Problem definition: Access to accurate predictions of patients' outcomes can enhance medical staff's decision-making, which ultimately benefits all stakeholders in the hospitals. A large hospital network in the US has been collaborating with academics and consultants to predict short-term and long-term outcomes for all inpatients across their seven hospitals. Methodology/results: We develop machine learning models that predict the probabilities of next 24-hr/48-hr discharge and intensive care unit transfers, end-of-stay mortality and discharge dispositions. All models achieve high out-of-sample AUC (75.7%-92.5%) and are well calibrated. In addition, combining 48-hr discharge predictions with doctors' predictions simultaneously enables more patient discharges (10%-28.7%) and fewer 7-day/30-day readmissions ($p$-value $<0.001$). We implement an automated pipeline that extracts data and updates predictions every morning, as well as user-friendly software and a color-coded alert system to communicate these patient-level predictions (alongside explanations) to clinical teams. Managerial implications: Since we have been gradually deploying the tool, and training medical staff, over 200 doctors, nurses, and case managers across seven hospitals use it in their daily patient review process. We observe a significant reduction in the average length of stay (0.67 days per patient) following its adoption and anticipate substantial financial benefits (between \$55 and \$72 million annually) for the healthcare system.

The agnostic setting is the hardest generalization of the PAC model since it is akin to learning with adversarial noise. In this paper, we give a poly$(n,t,{\frac{1}{\varepsilon}})$ quantum algorithm for learning size $t$ decision trees with uniform marginal over instances, in the agnostic setting, without membership queries. Our algorithm is the first algorithm (classical or quantum) for learning decision trees in polynomial time without membership queries. We show how to construct a quantum agnostic weak learner by designing a quantum version of the classical Goldreich-Levin algorithm that works with strongly biased function oracles. We show how to quantize the agnostic boosting algorithm by Kalai and Kanade (NIPS 2009) to obtain the first efficient quantum agnostic boosting algorithm. Our quantum boosting algorithm has a polynomial improvement in the dependence of the bias of the weak learner over all adaptive quantum boosting algorithms while retaining the standard speedup in the VC dimension over classical boosting algorithms. We then use our quantum boosting algorithm to boost the weak quantum learner we obtained in the previous step to obtain a quantum agnostic learner for decision trees. Using the above framework, we also give quantum decision tree learning algorithms for both the realizable setting and random classification noise model, again without membership queries.

Gradient Boosting Decision Tree (GBDT) has achieved remarkable success in a wide variety of applications. The split finding algorithm, which determines the tree construction process, is one of the most crucial components of GBDT. However, the split finding algorithm has long been criticized for its bias towards features with a large number of potential splits. This bias introduces severe interpretability and overfitting issues in GBDT. To this end, we provide a fine-grained analysis of bias in GBDT and demonstrate that the bias originates from 1) the systematic bias in the gain estimation of each split and 2) the bias in the split finding algorithm resulting from the use of the same data to evaluate the split improvement and determine the best split. Based on the analysis, we propose unbiased gain, a new unbiased measurement of gain importance using out-of-bag samples. Moreover, we incorporate the unbiased property into the split finding algorithm and develop UnbiasedGBM to solve the overfitting issue of GBDT. We assess the performance of UnbiasedGBM and unbiased gain in a large-scale empirical study comprising 60 datasets and show that: 1) UnbiasedGBM exhibits better performance than popular GBDT implementations such as LightGBM, XGBoost, and Catboost on average on the 60 datasets and 2) unbiased gain achieves better average performance in feature selection than popular feature importance methods. The codes are available at https://github.com/ZheyuAqaZhang/UnbiasedGBM.

Fraud detection is to identify, monitor, and prevent potentially fraudulent activities from complex data. The recent development and success in AI, especially machine learning, provides a new data-driven way to deal with fraud. From a methodological point of view, machine learning based fraud detection can be divided into two categories, i.e., conventional methods (decision tree, tree boosting methods...) and deep learning, both of which have significant limitations in terms of the lack of representation learning ability for the former and interpretability for the latter. Furthermore, due to the rarity of detected fraud cases, the associated data is usually imbalanced, which seriously degrades the performance of classification algorithms. In this paper, we propose deep boosting decision trees (DBDT), a novel approach for fraud detection based on gradient boosting and neural networks. In order to combine the advantages of both conventional methods and deep learning, we first construct soft decision tree (SDT), a decision tree structured model with neural networks as its nodes, and then ensemble SDTs using the idea of gradient boosting. In this way we embed neural networks into gradient boosting to improve its representation learning capability and meanwhile maintain the interpretability. Furthermore, aiming at the rarity of detected fraud cases, in the model training phase we propose a compositional AUC maximization approach to deal with data imbalances at algorithm level. Extensive experiments on several real-life fraud detection datasets show that DBDT can significantly improve the performance and meanwhile maintain good interpretability.

The quest for low-cost fusion power has led to the construction of experimental devices such as the DIII-D[8], an operational device for conducting magnetic fusion research, and ITER [16], an international project to help make the transition from studies of plasma physics to electricity-generating fusion power plants. These devices, called tokamaks, use magnetic fields to confine the fusion fuel in the form of a plasma, enabling physicists to perform experiments to determine the best shape for the hot reacting plasma and the magnetic fields necessary to hold it in place. To complement the experiments, computer simulations are used to gain an understanding of the complex physics of the plasmas, design new reactors, and select the parameters to be used in experiments. Data from both the experiments and the simulations are analyzed to provide the insights that will contribute to achieving the goal of fusion power. In this paper, we focus on a specific analysis problem that arises in both simulation and experimental data, namely, the classification of orbits in a Poincaré map, also called a Poincaré plot. These two-dimensional plots are obtained for planes, called poloidal planes, which intersect the torus-shaped tokamak perpendicular to the magnetic axis, as shown in Figure 1(a). A plot consists of several orbits, each composed of a number of points (Figure 1(b)). For a given orbit, these points are the intersections of a field line (the solid lines in Figure 1(a)) with a poloidal plane, as the field line is followed around the torus. There are four distinct shapes traced out by these points, leading to four classes of orbits: quasi-periodic, separatrix, island chain, and stochastic, as shown in Figure 2. In some cases, the orbit shows its distinctive shape with just a few points, corresponding to the first few intersections of the field line with the poloidal plane.

The random forest (RF) algorithm has become a very popular prediction method for its great flexibility and promising accuracy. In RF, it is conventional to put equal weights on all the base learners (trees) to aggregate their predictions. However, the predictive performances of different trees within the forest can be very different due to the randomization of the embedded bootstrap sampling and feature selection. In this paper, we focus on RF for regression and propose two optimal weighting algorithms, namely the 1 Step Optimal Weighted RF (1step-WRF$_\mathrm{opt}$) and 2 Steps Optimal Weighted RF (2steps-WRF$_\mathrm{opt}$), that combine the base learners through the weights determined by weight choice criteria. Under some regularity conditions, we show that these algorithms are asymptotically optimal in the sense that the resulting squared loss and risk are asymptotically identical to those of the infeasible but best possible model averaging estimator. Numerical studies conducted on real-world data sets indicate that these algorithms outperform the equal-weight forest and two other weighted RFs proposed in existing literature in most cases.