Related papers: A Dutch-Book Trap for Misspecification
We deal with the \textit{selective classification} problem (supervised-learning problem with a rejection option), where we want to achieve the best performance at a certain level of coverage of the data. We transform the original $m$-class…
I study endogenous learning dynamics for people who misperceive intertemporal correlations in random sequences. Biased agents face an optimal-stopping problem. They are uncertain about the underlying distribution and learn its parameters…
Simultaneous ascending auctions present agents with the exposure problem: bidding to acquire a bundle risks the possibility of obtaining an undesired subset of the goods. Auction theory provides little guidance for dealing with this…
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…
Suppose an investor aims at Delta hedging a European contingent claim $h(S(T))$ in a jump-diffusion model, but incorrectly specifies the stock price's volatility and jump sensitivity, so that any hedging strategy is calculated under a…
In M-open problems where no true model can be conceptualized, it is common to back off from modeling and merely seek good prediction. Even in M-complete problems, taking a predictive approach can be very useful. Stacking is a model…
Persuasion games are fundamental in economics and AI research and serve as the basis for important applications. However, work on this setup assumes communication with stylized messages that do not consist of rich human language. In this…
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent. The principal and the agent have misaligned objectives and the choice of action is only left to the…
Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand the agent's subjective reward range to include a large negative value $-L$, while the true…
Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an…
In this work, we consider classification of agents who can both game and improve. For example, people wishing to get a loan may be able to take some actions that increase their perceived credit-worthiness and others that also increase their…
This work studies a dynamic mechanism design problem in which a principal delegates decision makings to a group of privately-informed agents without the monetary transfer or burning. We consider that the principal privately possesses…
Detecting if a text is humorous is a hard task to do computationally, as it usually requires linguistic and common sense insights. In machine learning, humor detection is usually modeled as a binary classification task, trained to predict…
I study a principal-agent model in which a principal hires an agent to collect information about an unknown continuous state. The agent acquires a signal whose distribution is centered around the state, controlling the signal's precision at…
Corrigibility of autonomous agents is an under explored part of system design, with previous work focusing on single agent systems. It has been suggested that uncertainty over the human preferences acts to keep the agents corrigible, even…
Most bandit algorithms assume that the reward variances or their upper bounds are known, and that they are the same for all arms. This naturally leads to suboptimal performance and higher regret due to variance overestimation. On the other…
Sequences of repeated gambles provide an experimental tool to characterize the risk preferences of humans or artificial decision-making agents. The difficulty of this inference depends on factors including the details of the gambles offered…
This work studies the problem of non-Bayesian learning over multi-agent network when there are some adversarial (faulty) agents in the network. At each time step, each non-faulty agent collects partial information about an unknown state of…
We consider two-sided matching markets, and study the incentives of agents to circumvent a centralized clearing house by signing binding contracts with one another. It is well-known that if the clearing house implements a stable match and…
We formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. We demonstrate that while query nesting allows the definition of models which could not otherwise be expressed,…