The use of machine learning to guide clinical decision making has the potential to worsen existing health disparities. Several recent works frame the problem as that of algorithmic fairness, a framework that has attracted considerable attention and criticism. However, the appropriateness of this framework is unclear due to both ethical as well as technical considerations, the latter of which include trade-offs between measures of fairness and model performance that are not well-understood for predictive models of clinical outcomes. To inform the ongoing debate, we conduct an empirical study to characterize the impact of penalizing group fairness violations on an array of measures of model performance and group fairness. We repeat the analyses across multiple observational healthcare databases, clinical outcomes, and sensitive attributes. We find that procedures that penalize differences between the distributions of predictions across groups induce nearly-universal degradation of multiple performance metrics within groups. On examining the secondary impact of these procedures, we observe heterogeneity of the effect of these procedures on measures of fairness in calibration and ranking across experimental conditions. Beyond the reported trade-offs, we emphasize that analyses of algorithmic fairness in healthcare lack the contextual grounding and causal awareness necessary to reason about the mechanisms that lead to health disparities, as well as about the potential of algorithmic fairness methods to counteract those mechanisms. In light of these limitations, we encourage researchers building predictive models for clinical use to step outside the algorithmic fairness frame and engage critically with the broader sociotechnical context surrounding the use of machine learning in healthcare.

This is a short communication on a Lyapunov function argument for softmax in bandit problems. There are a number of excellent papers coming out using differential equations for policy gradient algorithms in reinforcement learning \cite{agarwal2019optimality,bhandari2019global,mei2020global}. We give a short argument that gives a regret bound for the soft-max ordinary differential equation for bandit problems. We derive a similar result for a different policy gradient algorithm, again for bandit problems. For this second algorithm, it is possible to prove regret bounds in the stochastic case \cite{DW20}. At the end, we summarize some ideas and issues on deriving stochastic regret bounds for policy gradients.

Network (or graph) embedding is the task to map the nodes of a graph to a lower dimensional vector space, such that it preserves the graph properties and facilitates the downstream network mining tasks. Real world networks often come with (community) outlier nodes, which behave differently from the regular nodes of the community. These outlier nodes can affect the embedding of the regular nodes, if not handled carefully. In this paper, we propose a novel unsupervised graph embedding approach (called DMGD) which integrates outlier and community detection with node embedding. We extend the idea of deep support vector data description to the framework of graph embedding when there are multiple communities present in the given network, and an outlier is characterized relative to its community. We also show the theoretical bounds on the number of outliers detected by DMGD. Our formulation boils down to an interesting minimax game between the outliers, community assignments and the node embedding function. We also propose an efficient algorithm to solve this optimization framework. Experimental results on both synthetic and real world networks show the merit of our approach compared to state-of-the-arts.

This work is devoted to the finite sample prediction risk analysis of a class of linear predictors of a response $Y\in \mathbb{R}$ from a high-dimensional random vector $X\in \mathbb{R}^p$ when $(X,Y)$ follows a latent factor regression model generated by a unobservable latent vector $Z$ of dimension less than $p$. Our primary contribution is in establishing finite sample risk bounds for prediction with the ubiquitous Principal Component Regression (PCR) method, under the factor regression model, with the number of principal components adaptively selected from the data---a form of theoretical guarantee that is surprisingly lacking from the PCR literature. To accomplish this, we prove a master theorem that establishes a risk bound for a large class of predictors, including the PCR predictor as a special case. This approach has the benefit of providing a unified framework for the analysis of a wide range of linear prediction methods, under the factor regression setting. In particular, we use our main theorem to recover known risk bounds for the minimum-norm interpolating predictor, which has received renewed attention in the past two years, and a prediction method tailored to a subclass of factor regression models with identifiable parameters. This model-tailored method can be interpreted as prediction via clusters with latent centers. To address the problem of selecting among a set of candidate predictors, we analyze a simple model selection procedure based on data-splitting, providing an oracle inequality under the factor model to prove that the performance of the selected predictor is close to the optimal candidate. We conclude with a detailed simulation study to support and complement our theoretical results.

Purpose: This paper presents an algorithm that can elicitate (infer) all or any combination of ELECTRE Tri-B parameters. For example, a decision-maker can maintain the values for indifference, preference, and veto thresholds, and our algorithm can find the criteria weights, reference profiles, and the lambda cutting level. Our approach is inspired by a Machine Learning ensemble technique, the Random Forest, and for that, we named our approach as ELECTRE Tree algorithm. Methodology: First, we generate a set of ELECTRE Tri-B models, where each model solves a random sample of criteria and alternatives. Each sample is made with replacement, having at least two criteria and between 10% to 25% of alternatives. Each model has its parameters optimized by a genetic algorithm that can use an ordered cluster or an assignment example as a reference to the optimization. Finally, after the optimization phase, two procedures can be performed, the first one will merge all models, finding in this way the elicitated parameters, and in the second procedure each alternative is classified (voted) by each separated model, and the majority vote decides the final class. Findings: We have noted that concerning the voting procedure, non-linear decision boundaries are generated, and they can be suitable in analyzing problems with the same nature. In contrast, the merged model generates linear decision boundaries. Originality: The elicitation of ELECTRE Tri-B parameters is made by an ensemble technique that is composed of a set of multicriteria models that are engaged in generating robust solutions.

Investigating the cognitive and neural mechanisms involved with face processing is a fundamental task in modern neuroscience and psychology. To date, the majority of such studies have focused on the use of pre-selected stimuli. The absence of personalized stimuli presents a serious limitation as it fails to account for how each individual face processing system is tuned to cultural embeddings or how it is disrupted in disease. In this work, we propose a novel framework which combines generative adversarial networks (GANs) with Bayesian optimization to identify individual response patterns to many different faces. Formally, we employ Bayesian optimization to efficiently search the latent space of state-of-the-art GAN models, with the aim to automatically generate novel faces, to maximize an individual subject's response. We present results from a web-based proof-of-principle study, where participants rated images of themselves generated via performing Bayesian optimization over the latent space of a GAN. We show how the algorithm can efficiently locate an individual's optimal face while mapping out their response across different semantic transformations of a face; inter-individual analyses suggest how the approach can provide rich information about individual differences in face processing.

Multiple Kernel Learning is a recent and powerful paradigm to learn the kernel function from data. In this paper, we introduce MKLpy, a python-based framework for Multiple Kernel Learning. The library provides Multiple Kernel Learning algorithms for classification tasks, mechanisms to compute kernel functions for different data types, and evaluation strategies. The library is meant to maximize the usability and to simplify the development of novel solutions.

Explanation methods promise to make black-box classifiers more transparent. As a result, it is hoped that they can act as proof for a sensible, fair and trustworthy decision-making process of the algorithm and thereby increase its acceptance by the end-users. In this paper, we show both theoretically and experimentally that these hopes are presently unfounded. Specifically, we show that, for any classifier $g$, one can always construct another classifier $\tilde{g}$ which has the same behavior on the data (same train, validation, and test error) but has arbitrarily manipulated explanation maps. We derive this statement theoretically using differential geometry and demonstrate it experimentally for various explanation methods, architectures, and datasets. Motivated by our theoretical insights, we then propose a modification of existing explanation methods which makes them significantly more robust.

Hyperparameters play a critical role in the performances of many machine learning methods. Determining their best settings or Hyperparameter Optimization (HPO) faces difficulties presented by the large number of hyperparameters as well as the excessive training time. In this paper, we develop an effective approach to reducing the total amount of required training time for HPO. In the initialization, the nested Latin hypercube design is used to select hyperparameter configurations for two types of training, which are, respectively, heavy training and light training. We propose a truncated additive Gaussian process model to calibrate approximate performance measurements generated by light training, using accurate performance measurements generated by heavy training. Based on the model, a sequential model-based algorithm is developed to generate the performance profile of the configuration space as well as find optimal ones. Our proposed approach demonstrates competitive performance when applied to optimize synthetic examples, support vector machines, fully connected networks and convolutional neural networks.

Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges. We show that deep-ensembles do not necessarily lead to improved calibration properties. In fact, we show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. In this text, we examine the interplay between three of the most simple and commonly used approaches to leverage deep learning when data is scarce: data-augmentation, ensembling, and post-processing calibration methods. We demonstrate that, although standard ensembling techniques certainly help to boost accuracy, the calibration of deep-ensembles relies on subtle trade-offs. Our main finding is that calibration methods such as temperature scaling need to be slightly tweaked when used with deep-ensembles and, crucially, need to be executed after the averaging process. Our simulations indicate that, in the low data regime, this simple strategy can halve the Expected Calibration Error (ECE) on a range of benchmark classification problems when compared to standard deep-ensembles.