The rapid integration of machine learning (ML) predictors into in silico medicine has revolutionized the estimation of quantities of interest (QIs) that are otherwise challenging to measure directly. However, the credibility of these predictors is critical, especially when they inform high-stakes healthcare decisions. This position paper presents a consensus statement developed by experts within the In Silico World Community of Practice. We outline twelve key statements forming the theoretical foundation for evaluating the credibility of ML predictors, emphasizing the necessity of causal knowledge, rigorous error quantification, and robustness to biases. By comparing ML predictors with biophysical models, we highlight unique challenges associated with implicit causal knowledge and propose strategies to ensure reliability and applicability. Our recommendations aim to guide researchers, developers, and regulators in the rigorous assessment and deployment of ML predictors in clinical and biomedical contexts.

A standard tool for modelling real-world optimisation problems is mixed-integer programming (MIP). However, for many of these problems there is either incomplete information describing variable relations, or the relations between variables are highly complex. To overcome both these hurdles, machine learning (ML) models are often used and embedded in the MIP as surrogate models to represent these relations. Due to the large amount of available ML frameworks, formulating ML models into MIPs is highly non-trivial. In this paper we propose a tool for the automatic MIP formulation of trained ML models, allowing easy integration of ML constraints into MIPs. In addition, we introduce a library of MIP instances with embedded ML constraints. The project is available at https://github.com/Opt-Mucca/PySCIPOpt-ML.

We introduce a novel loss function to minimize the outage probability of an ML-based resource allocation system. A single-user multi-resource greedy allocation strategy constitutes our application scenario, for which an ML binary classification predictor assists in selecting a resource satisfying the established outage criterium. While other resource allocation policies may be suitable, they are not the focus of our study. Instead, our primary emphasis is on theoretically developing this loss function and leveraging it to train an ML model to address the outage probability challenge. With no access to future channel state information, this predictor foresees each resource's likely future outage status. When the predictor encounters a resource it believes will be satisfactory, it allocates it to the user. Our main result establishes exact and asymptotic expressions for this system's outage probability. These expressions reveal that focusing solely on the optimization of the per-resource outage probability conditioned on the ML predictor recommending resource allocation (a strategy that appears to be most appropriate) may produce inadequate predictors that reject every resource. They also reveal that focusing on standard metrics, like precision, false-positive rate, or recall, may not produce optimal predictors. With our result, we formulate a theoretically optimal, differentiable loss function to train our predictor. We then compare predictors trained using this and traditional loss functions namely, binary cross-entropy (BCE), mean squared error (MSE), and mean absolute error (MAE). In all scenarios, predictors trained using our novel loss function provide superior outage probability performance. Moreover, in some cases, our loss function outperforms predictors trained with BCE, MAE, and MSE by multiple orders of magnitude.

As the competition among machine learning (ML) predictors is widespread in practice, it becomes increasingly important to understand the impact and biases arising from such competition. One critical aspect of ML competition is that ML predictors are constantly updated by acquiring additional data during the competition. Although this active data acquisition can largely affect the overall competition environment, it has not been well-studied before. In this paper, we study what happens when ML predictors can purchase additional data during the competition. We introduce a new environment in which ML predictors use active learning algorithms to effectively acquire labeled data within their budgets while competing against each other. We empirically show that the overall performance of an ML predictor improves when predictors can purchase additional labeled data. Surprisingly, however, the quality that users experience--i.e., the accuracy of the predictor selected by each user--can decrease even as the individual predictors get better. We demonstrate that this phenomenon naturally arises due to a trade-off whereby competition pushes each predictor to specialize in a subset of the population while data purchase has the effect of making predictors more uniform. With comprehensive experiments, we show that our findings are robust against different modeling assumptions.

"Netflix and Amazon compete to provide the customers with best recommendations. But algorithm feedback dynamics could lead to real problems." Algorithms competing to recommend a better movie is not a problem, but when they are tasked with hiring or granting loans, it can become a huge problem. Researchers at Stanford's Artificial Intelligence department published a work enquiring how algorithms that compete for clicks and the associated user data become more specialised for subpopulations that gravitate to their sites. In a new paper, titled "Competing AI", the researchers talk about how this phenomenon can have serious implications for both companies and consumers.

Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. In this paper, we propose two algorithms that adjust fitted ML predictors to make them fair. We focus on two legal notions of fairness: (a) providing equal opportunity (EO) to individuals regardless of sensitive attributes and (b) repairing historical disadvantages through affirmative action (AA). More technically, we produce fair EO and AA predictors by positing a causal model and considering counterfactual decisions. We prove that the resulting predictors are theoretically optimal in predictive performance while satisfying fairness. We evaluate the algorithms, and the trade-offs between accuracy and fairness, on datasets about admissions, income, credit and recidivism.