Decision trees are powerful tools for classification and regression that attract many researchers working in the burgeoning area of machine learning. One advantage of decision trees over other methods is their interpretability, which is often preferred over other higher accuracy methods that are relatively uninterpretable. A binary classification tree has two types of vertices: (i) branching vertices which have exactly two children and where datapoints are assessed on a set of discrete features; and (ii) leaf vertices at which datapoints are given a discrete prediction. An optimal binary classification tree can be obtained by solving a biobjective optimization problem that seeks to (i) maximize the number of correctly classified datapoints and (ii) minimize the number of branching vertices. In this paper, we propose four mixed integer linear optimization (MILO) formulations for designing optimal binary classification trees: two flow-based formulations and two-cut based formulations. We provide theoretical comparisons between our proposed formulations and the strongest flow-based MILO formulation of Aghaei et al. (2021). We conduct experiments on 13 publicly available datasets to show the models' ability to scale and the strength of a biobjective approach using Pareto frontiers. Our code and data are available on GitHub.

We prove that it is NP-hard to properly PAC learn decision trees with queries, resolving a longstanding open problem in learning theory (Bshouty 1993; Guijarro-Lavin-Raghavan 1999; Mehta-Raghavan 2002; Feldman 2016). While there has been a long line of work, dating back to (Pitt-Valiant 1988), establishing the hardness of properly learning decision trees from random examples, the more challenging setting of query learners necessitates different techniques and there were no previous lower bounds. En route to our main result, we simplify and strengthen the best known lower bounds for a different problem of Decision Tree Minimization (Zantema-Bodlaender 2000; Sieling 2003). On a technical level, we introduce the notion of hardness distillation, which we study for decision tree complexity but can be considered for any complexity measure: for a function that requires large decision trees, we give a general method for identifying a small set of inputs that is responsible for its complexity. Our technique even rules out query learners that are allowed constant error. This contrasts with existing lower bounds for the setting of random examples which only hold for inverse-polynomial error. Our result, taken together with a recent almost-polynomial time query algorithm for properly learning decision trees under the uniform distribution (Blanc-Lange-Qiao-Tan 2022), demonstrates the dramatic impact of distributional assumptions on the problem.

Decision tree learning is increasingly being used for pointwise inference. Important applications include causal heterogenous treatment effects and dynamic policy decisions, as well as conditional quantile regression and design of experiments, where tree estimation and inference is conducted at specific values of the covariates. In this paper, we call into question the use of decision trees (trained by adaptive recursive partitioning) for such purposes by demonstrating that they can fail to achieve polynomial rates of convergence in uniform norm, even with pruning. Instead, the convergence may be poly-logarithmic or, in some important special cases, such as honest regression trees, fail completely. We show that random forests can remedy the situation, turning poor performing trees into nearly optimal procedures, at the cost of losing interpretability and introducing two additional tuning parameters. The two hallmarks of random forests, subsampling and the random feature selection mechanism, are seen to each distinctively contribute to achieving nearly optimal performance for the model class considered.

Using Machine Learning systems in the real world can often be problematic, with inexplicable black-box models, the assumed certainty of imperfect measurements, or providing a single classification instead of a probability distribution. This paper introduces Indecision Trees, a modification to Decision Trees which learn under uncertainty, can perform inference under uncertainty, provide a robust distribution over the possible labels, and can be disassembled into a set of logical arguments for use in other reasoning systems.

Understanding differences between sub-stellar spectral data and models has proven to be a major challenge, especially for self-consistent model grids that are necessary for a thorough investigation of brown dwarf atmospheres. Using the supervised machine learning method of the random forest, we study the information content of 14 previously published model grids of brown dwarfs (from 1997 to 2021). The random forest method allows us to analyze the predictive power of these model grids, as well as interpret data within the framework of Approximate Bayesian Computation (ABC). Our curated dataset includes 3 benchmark brown dwarfs (Gl 570D, {\epsilon} Indi Ba and Bb) as well as a sample of 19 L and T dwarfs; this sample was previously analyzed in Lueber et al. (2022) using traditional Bayesian methods (nested sampling). We find that the effective temperature of a brown dwarf can be robustly predicted independent of the model grid chosen for the interpretation. However, inference of the surface gravity is model-dependent. Specifically, the BT-Settl, Sonora Bobcat and Sonora Cholla model grids tend to predict logg ~3-4 (cgs units) even after data blueward of 1.2 {\mu}m have been disregarded to mitigate for our incomplete knowledge of the shapes of alkali lines. Two major, longstanding challenges associated with understanding the influence of clouds in brown dwarf atmospheres remain: our inability to model them from first principles and also to robustly validate these models.

Our capacity to process large complex data sources is ever-increasing, providing us with new, important applied research questions to address, such as how to handle missing values in large-scale databases. Mitra et al. (2023) noted the phenomenon of Structured Missingness (SM), which is where missingness has an underlying structure. Existing taxonomies for defining missingness mechanisms typically assume that variables' missingness indicator vectors $M_1$, $M_2$, ..., $M_p$ are independent after conditioning on the relevant portion of the data matrix $\mathbf{X}$. As this is often unsuitable for characterising SM in multivariate settings, we introduce a taxonomy for SM, where each ${M}_j$ can depend on $\mathbf{M}_{-j}$ (i.e., all missingness indicator vectors except ${M}_j$), in addition to $\mathbf{X}$. We embed this new framework within the well-established decomposition of mechanisms into MCAR, MAR, and MNAR (Rubin, 1976), allowing us to recast mechanisms into a broader setting, where we can consider the combined effect of $\mathbf{X}$ and $\mathbf{M}_{-j}$ on ${M}_j$. We also demonstrate, via simulations, the impact of SM on inference and prediction, and consider contextual instances of SM arising in a de-identified nationwide (US-based) clinico-genomic database (CGDB). We hope to stimulate interest in SM, and encourage timely research into this phenomenon.

Background: Reliable prediction of clinical progression over time can improve the outcomes of depression. Little work has been done integrating various risk factors for depression, to determine the combinations of factors with the greatest utility for identifying which individuals are at the greatest risk. Method: This study demonstrates that data-driven machine learning (ML) methods such as RE-EM (Random Effects/Expectation Maximization) trees and MERF (Mixed Effects Random Forest) can be applied to reliably identify variables that have the greatest utility for classifying subgroups at greatest risk for depression. 185 young adults completed measures of depression risk, including rumination, worry, negative cognitive styles, cognitive and coping flexibilities, and negative life events, along with symptoms of depression. We trained RE-EM trees and MERF algorithms and compared them to traditional linear mixed models (LMMs) predicting depressive symptoms prospectively and concurrently with cross-validation. Results: Our results indicated that the RE-EM tree and MERF methods model complex interactions, identify subgroups of individuals and predict depression severity comparable to LMM. Further, machine learning models determined that brooding, negative life events, negative cognitive styles, and perceived control were the most relevant predictors of future depression levels. Conclusions: Random effects machine learning models have the potential for high clinical utility and can be leveraged for interventions to reduce vulnerability to depression.

Although being a crucial question for the development of machine learning algorithms, there is still no consensus on how to compare classifiers over multiple data sets with respect to several criteria. Every comparison framework is confronted with (at least) three fundamental challenges: the multiplicity of quality criteria, the multiplicity of data sets and the randomness of the selection of data sets. In this paper, we add a fresh view to the vivid debate by adopting recent developments in decision theory. Based on so-called preference systems, our framework ranks classifiers by a generalized concept of stochastic dominance, which powerfully circumvents the cumbersome, and often even self-contradictory, reliance on aggregates. Moreover, we show that generalized stochastic dominance can be operationalized by solving easy-to-handle linear programs and moreover statistically tested employing an adapted two-sample observation-randomization test. This yields indeed a powerful framework for the statistical comparison of classifiers over multiple data sets with respect to multiple quality criteria simultaneously. We illustrate and investigate our framework in a simulation study and with a set of standard benchmark data sets.

Mean decrease in impurity (MDI) is a popular feature importance measure for random forests (RFs). We show that the MDI for a feature $X_k$ in each tree in an RF is equivalent to the unnormalized $R^2$ value in a linear regression of the response on the collection of decision stumps that split on $X_k$. We use this interpretation to propose a flexible feature importance framework called MDI+. Specifically, MDI+ generalizes MDI by allowing the analyst to replace the linear regression model and $R^2$ metric with regularized generalized linear models (GLMs) and metrics better suited for the given data structure. Moreover, MDI+ incorporates additional features to mitigate known biases of decision trees against additive or smooth models. We further provide guidance on how practitioners can choose an appropriate GLM and metric based upon the Predictability, Computability, Stability framework for veridical data science. Extensive data-inspired simulations show that MDI+ significantly outperforms popular feature importance measures in identifying signal features. We also apply MDI+ to two real-world case studies on drug response prediction and breast cancer subtype classification. We show that MDI+ extracts well-established predictive genes with significantly greater stability compared to existing feature importance measures. All code and models are released in a full-fledged python package on Github.

During the past decade, metal additive manufacturing (MAM) has experienced significant developments and gained much attention due to its ability to fabricate complex parts, manufacture products with functionally graded materials, minimize waste, and enable low-cost customization. Despite these advantages, predicting the impact of processing parameters on the characteristics of an MAM printed clad is challenging due to the complex nature of MAM processes. Machine learning (ML) techniques can help connect the physics underlying the process and processing parameters to the clad characteristics. In this study, we introduce a hybrid approach which involves utilizing the data provided by a calibrated multi-physics computational fluid dynamic (CFD) model and experimental research for preparing the essential big dataset, and then uses a comprehensive framework consisting of various ML models to predict and understand clad characteristics. We first compile an extensive dataset by fusing experimental data into the data generated using the developed CFD model for this study. This dataset comprises critical clad characteristics, including geometrical features such as width, height, and depth, labels identifying clad quality, and processing parameters. Second, we use two sets of processing parameters for training the ML models: machine setting parameters and physics-aware parameters, along with versatile ML models and reliable evaluation metrics to create a comprehensive and scalable learning framework for predicting clad geometry and quality. This framework can serve as a basis for clad characteristics control and process optimization. The framework resolves many challenges of conventional modeling methods in MAM by solving t the issue of data scarcity using a hybrid approach and introducing an efficient, accurate, and scalable platform for clad characteristics prediction and optimization.