Related papers: Reputational Conservatism in Expert Advice
In this paper, we consider the problem of making skeptical inferences for the multi-label ranking problem. We assume that our uncertainty is described by a convex set of probabilities (i.e. a credal set), defined over the set of labels.…
The paper has 2 main goals: 1. We propose a variant of the CAPM based on coherent risk. 2. In addition to the real-world measure and the risk-neutral measure, we propose the third one: the extreme measure. The introduction of this measure…
Consider a predictor who ranks eventualities on the basis of past cases: for instance a search engine ranking webpages given past searches. Resampling past cases leads to different rankings and the extraction of deeper information. Yet a…
This paper develops a framework to study the statistical power of revealed-preference tests. With randomly sampled budgets and mild smoothness of demand, statistical learning implies that any model consistent with the data must approximate…
This paper provides a behavioral analysis of conservatism in beliefs. I introduce a new axiom, Dynamic Conservatism, that relaxes Dynamic Consistency when information and prior beliefs "conflict." When the agent is a subjective expected…
This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…
Cooperation in human society is sustained by reputation. In general, the reputation of an individual is determined by others who observe his behavior, but this rarely happens in private situations. This may cause people to behave…
We study optimal rating design under moral hazard and strategic manipulation. An intermediary observes a noisy indicator of effort and commits to a rating policy that shapes market beliefs and pay. We characterize optimal ratings via…
A recent body of work addresses safety constraints in explore-and-exploit systems. Such constraints arise where, for example, exploration is carried out by individuals whose welfare should be balanced with overall welfare. In this paper, we…
We study a reputational cheap-talk environment in which a judge, who is privately and imperfectly informed about a state, must choose between two speakers of unknown reliability. Exactly one speaker is an expert who perfectly observes the…
The tendency of repeating past choices more often than expected from the history of outcomes has been repeatedly empirically observed in reinforcement learning experiments. It can be explained by at least two computational processes:…
We study optimal taxation when citizens hold beliefs about an honest versus opportunistic government and update those beliefs from observed taxes and delivery. In a Ramsey economy with competitive firms, the government privately knows its…
Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the recommendations as well as the recommendations of other…
We study the problem of prediction with expert advice with adversarial corruption where the adversary can at most corrupt one expert. Using tools from viscosity theory, we characterize the long-time behavior of the value function of the…
Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the…
This paper studies an exponential bandit model in which a group of agents collectively decide whether to undertake a risky action $R$. This action is implemented if the fraction of agents voting for it exceeds a predetermined threshold $k$.…
Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…
Agents' learning from feedback shapes economic outcomes, and many economic decision-makers today employ learning algorithms to make consequential choices. This note shows that a widely used learning algorithm, $\varepsilon$-Greedy, exhibits…
We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-learning problem. A policy gateway maintains a Gaussian-process…
The cognitive research on reputation has shown several interesting properties that can improve both the quality of services and the security in distributed electronic environments. In this paper, the impact of reputation on decision-making…