Related papers: Beyond Ads: Sequential Decision-Making Algorithms …

Sequential portfolio selection has attracted increasing interests in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed…

Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc . Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to…

We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of…

Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions…

We address the challenge of finding algorithms for online allocation (i.e. bipartite matching) using a machine learning approach. In this paper, we focus on the AdWords problem, which is a classical online budgeted matching problem of both…

Machine learning has witnessed remarkable breakthroughs in recent years. As machine learning permeates various aspects of daily life, individuals and organizations increasingly interact with these systems, exhibiting a wide range of social…

Predictive algorithms are now used to help distribute a large share of our society's resources and sanctions, such as healthcare, loans, criminal detentions, and tax audits. Under the right circumstances, these algorithms can improve the…

Machine learning has the potential to fuel further advances in data science, but it is greatly hindered by an ad hoc design process, poor data hygiene, and a lack of statistical rigor in model evaluation. Recently, these issues have begun…

Machine learning is increasingly used in the legal domain, where it typically operates retrospectively by treating past case outcomes as ground truth. However, legal outcomes are often shaped by human interventions that are not captured in…

In a multi-armed bandit (MAB) problem, an online algorithm makes a sequence of choices. In each round it chooses from a time-invariant set of alternatives and receives the payoff associated with this alternative. While the case of small…

Regulations govern many aspects of citizens' daily lives. Governments and businesses routinely automate these in the form of coded rules (e.g., to check a citizen's eligibility for specific benefits). However, the path to automation is long…

Algorithms in public services such as child welfare, criminal justice, and education are increasingly being used to make high-stakes decisions about human lives. Drawing upon findings from a two-year ethnography conducted at a child welfare…

We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses in codified rules. Plaintiff and defendant agents choose from a constrained action space…

Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals from the same population. In reality, these prediction…

As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed…

Display Ads and the generalized assignment problem are two well-studied online packing problems with important applications in ad allocation and other areas. In both problems, ad impressions arrive online and have to be allocated…

Societies often rely on human experts to take a wide variety of decisions affecting their members, from jail-or-release decisions taken by judges and stop-and-frisk decisions taken by police officers to accept-or-reject decisions taken by…

Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the…

Prior work on the complexity of bribery assumes that the bribery happens simultaneously, and that the briber has full knowledge of all votes. However, in many real-world settings votes come in sequentially, and the briber may have a…

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…