Related papers: Hidden Incentives for Auto-Induced Distributional …

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…

The basic underlying assumption of machine learning (ML) models is that the training and test data are sampled from the same distribution. However, in daily practice, this assumption is often broken, i.e. the distribution of the test data…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

Research in artificial intelligence (AI)-assisted decision-making is experiencing tremendous growth with a constantly rising number of studies evaluating the effect of AI with and without techniques from the field of explainable AI (XAI) on…

While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where…

Industry has always been in the pursuit of becoming more economically efficient and the current focus has been to reduce human labour using modern technologies. Even with cutting edge technologies, which range from packaging robots to AI…

A dynamic autonomy allocation framework automatically shifts how much control lies with the human versus the robotics autonomy, for example based on factors such as environmental safety or user preference. To investigate the question of…

Artificial intelligence (AI)-based clinical decision support systems (CDSS) promise to enhance diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration might introduce automation bias, where users…

Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models, eliminating the need for direct real-world environment interaction. However, this paradigm is inherently challenged by…

A community of researchers appears to think that a machine can be surprised and have introduced various surprise measures, principally the Shannon Surprise and the Bayesian Surprise. The questions of what constitutes a surprise and how to…

I examine a conceptual model of a recommendation system (RS) with user inflow and churn dynamics. When inflow and churn balance out, the user distribution reaches a steady state. Changing the recommendation algorithm alters the steady state…

Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation,…

Machine learning systems often acquire biases by leveraging undesired features in the data, impacting accuracy variably across different sub-populations. Current understanding of bias formation mostly focuses on the initial and final stages…

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of…

Artificial intelligence (AI) is gaining momentum, and its importance for the future of work in many areas, such as medicine and banking, is continuously rising. However, insights on the effective collaboration of humans and AI are still…

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, fairness, and honesty. Transferring these behavioral properties to models trained on different tasks or data distributions remains…

Supervised machine learning often encounters concept drift, where the data distribution changes over time, degrading model performance. Existing drift detection methods focus on identifying these shifts but often overlook the challenge of…

When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e.g., by strategically modifying their features. The goal in strategic classification is therefore to train predictive models that…