Related papers: Unpacking the Black Box: Regulating Algorithmic De…
With increasing ubiquity of artificial intelligence (AI) in modern societies, individual countries and the international community are working hard to create an innovation-friendly, yet safe, regulatory environment. Adequate regulation is…
Recommender systems present a customized list of items based upon user or item characteristics with the objective of reducing a large number of possible choices to a smaller ranked set most likely to appeal to the user. A variety of…
Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on…
There is a growing demand for the use of Artificial Intelligence (AI) and Machine Learning (ML) in healthcare, particularly as clinical decision support systems to assist medical professionals. However, the complexity of many of these…
Lightweight fine-tuning techniques and the rise of 'open' AI model marketplaces have enabled individuals to easily build and release generative models. Yet, this accessibility also raises risks, including the production of harmful and…
We present a new multi-objective optimization approach for synthesizing interpretations that "explain" the behavior of black-box machine learning models. Constructing human-understandable interpretations for black-box models often requires…
There has been much discussion of the right to explanation in the EU General Data Protection Regulation, and its existence, merits, and disadvantages. Implementing a right to explanation that opens the black box of algorithmic…
When explaining black-box machine learning models, it's often important for explanations to have certain desirable properties. Most existing methods `encourage' desirable properties in their construction of explanations. In this work, we…
We present an interpretable companion model for any pre-trained black-box classifiers. The idea is that for any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or…
While high-stakes ML applications demand strict regulations, strategic ML providers often evade them to lower development costs. To address this challenge, we cast AI regulation as a mechanism design problem under uncertainty and introduce…
This paper is preoccupied with the following question: given a (possibly opaque) learning system, how can we understand whether its behaviour adheres to governance constraints? The answer can be quite simple: we just need to "ask" the…
Feature-based algorithm selection aims to automatically find the best one from a portfolio of optimization algorithms on an unseen problem based on its landscape features. Feature-based algorithm selection has recently received attention in…
Data-driven algorithmic matching systems promise to help human decision makers make better matching decisions in a wide variety of high-stakes application domains, such as healthcare and social service provision. However, existing systems…
Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results in low…
Prediction-oriented machine learning is becoming increasingly valuable to organizations, as it may drive applications in crucial business areas. However, decision-makers from companies across various industries are still largely reluctant…
Machine learning actively impacts our everyday life in almost all endeavors and domains such as healthcare, finance, and energy. As our dependence on the machine learning increases, it is inevitable that these algorithms will be used to…
Artificial Intelligence algorithms have now become pervasive in multiple high-stakes domains. However, their internal logic can be obscure to humans. Explainable Artificial Intelligence aims to design tools and techniques to illustrate the…
Calibration is a well-studied property of predictors which guarantees meaningful uncertainty estimates. Multicalibration is a related notion -- originating in algorithmic fairness -- which requires predictors to be simultaneously calibrated…
Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's…
A predominant topic in the theory of evolutionary algorithms and, more generally, theory of randomized black-box optimization techniques is running time analysis. Running time analysis aims at understanding the performance of a given…