Related papers: Emergent specialization from participation dynamic…

In decision-dependent games, multiple players optimize their decisions under a data distribution that shifts with their joint actions, creating complex dynamics in applications like market pricing. A practical consequence of these dynamics…

Modern social platforms are characterized by the presence of rich user-behavior data associated with the publication, sharing and consumption of textual content. Users interact with content and with each other in a complex and dynamic…

Despite extensive research, the mechanisms through which online platforms shape extremism and polarization remain poorly understood. We identify and test a mechanism, grounded in empirical evidence, that explains how ranking algorithms can…

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which…

Modern online services continuously generate data at very fast rates. This continuous flow of data encompasses content - e.g., posts, news, products, comments -, but also user feedback - e.g., ratings, views, reads, clicks -, together with…

Imitation is an important learning heuristic in animal and human societies. Previous explorations report that the fate of individuals with cooperative strategies is sensitive to the protocol of imitation, leading to a conundrum about how…

Empirical risk minimization stands behind most optimization in supervised machine learning. Under this scheme, labeled data is used to approximate an expected cost (risk), and a learning algorithm updates model-defining parameters in search…

Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this…

Our research is concerned with studying behavioural changes within a dynamic system, i.e. health care, and their effects on the decision-making process. Evolutionary Game theory is applied to investigate the most probable strategy(ies)…

We analyze the unintended effects that recommender systems have on the preferences of users that they are learning. We consider a contextual multi-armed bandit recommendation algorithm that learns optimal product recommendations based on…

In this paper, we address two practical challenges of distributed learning in multi-agent network systems, namely personalization and resilience. Personalization is the need of heterogeneous agents to learn local models tailored to their…

When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the…

How do networks of relationships evolve over time? We analyse a dataset tracking the social interactions of 900 individuals over four years. Despite continuous shifts in individual relationships, the macroscopic structural properties of the…

Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. While many federated learning architectures process data in an online manner, and are hence adaptive by nature, most…

This paper focuses on learning a model of system dynamics online while satisfying safety constraints.Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously…

Opinion dynamics models how the publicly expressed opinions of users in a social network coevolve according to their neighbors as well as their own intrinsic opinion. Motivated by the real-world manipulation of social networks during the…

Recommender systems daily influence our decisions on the Internet. While considerable attention has been given to issues such as recommendation accuracy and user privacy, the long-term mutual feedback between a recommender system and the…

We study the welfare of a mechanism in a dynamic environment where a learning investor can make a costly investment to change her value. In many real-world problems, the common assumption that the investor always makes the best responses,…

When users stand to gain from certain predictions, they are prone to act strategically to obtain favorable predictive outcomes. Whereas most works on strategic classification consider user actions that manifest as feature modifications, we…

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…