12 accepted papers
Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "l
AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes decision-making, we need accurate cognitively-aligned AI systems that reason similarly to their users, and faithfully c…
Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using standard preference elicitation methods, researchers and practitioners build models of human decisions and judgments, to which AI models are aligned. However…
We study fair allocation of constrained resources, where a market designer optimizes overall welfare while maintaining group fairness. In many large-scale settings, utilities are not known in advance, but are instead observed after realizing the allocation. We therefore estimate agent utilities usin…
In fair machine learning, one source of performance disparities between groups is overfitting to groups with relatively few training samples. We derive group-specific bounds on the generalization error of welfare-centric fair machine learning that benefit from the larger sample size of the majority…
In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion. The percentile criterion is optimized by constructing an uncertainty set that contains the true model with high probability and optimizin…
Cardinal objectives serve as intuitive targets in fair machine learning by summarizing utility (welfare) or disutility (malfare) $u$ over $g$ groups. Under standard axioms, all welfare and malfare functions are $w$-weighted $p$-power-means, i.e. $M_p(u;w) = \sqrt[p]{\sum_{i=1}^g w_i u_i^p}$, with $p…
We develop a rigorous approach for using a set of arbitrarily correlated weak supervision sources in order to solve a multiclass classification task when only a very small set of labeled data is available. Our learning algorithm provably converges to a model that has minimum empirical risk with resp…
We address an inherent difficulty in welfare-theoretic fair machine learning (ML), by proposing an equivalently-axiomatically justified alternative setting, and studying the resulting computational and statistical learning questions. Welfare metrics quantify overall wellbeing across a population of…
We present a novel method for reducing the computational complexity of rigorously estimating the partition functions of Gibbs (or Boltzmann) distributions, which arise ubiquitously in probabilistic graphical models. A major obstacle to applying the Gibbs distribution in practice is the need to estim…
We introduce the use of empirical centralization to derive novel practical, probabilistic, sample-dependent bounds to the Supremum Deviation (SD) of empirical means of functions in a family from their expectations. Our bounds have optimal dependence on the maximum (i.e., wimpy) variance and the func…
We introduce a methodology for the design of parametric mechanisms, which are multiagent systems inhabited by strategic agents, with knobs that can be adjusted to achieve specific goals. We assume agents play approximate equilibria, which we estimate using the probably approximately correct learning…