Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Chugg, Ben"'
We consider estimating the shared mean of a sequence of heavy-tailed random variables taking values in a Banach space. In particular, we revisit and extend a simple truncation-based mean estimator by Catoni and Giulini. While existing truncation-base
Externí odkaz:
http://arxiv.org/abs/2411.11271
We derive and study time-uniform confidence spheres -- confidence sphere sequences (CSSs) -- which contain the mean of random vectors with high probability simultaneously across all sample sizes. Our results include a dimension-free CSS for log-conca
Externí odkaz:
http://arxiv.org/abs/2311.08168
We provide practical, efficient, and nonparametric methods for auditing the fairness of deployed classification and regression models. Whereas previous work relies on a fixed-sample size, our methods are sequential and allow for the continuous monito
Externí odkaz:
http://arxiv.org/abs/2305.17570
We present a unified framework for deriving PAC-Bayesian generalization bounds. Unlike most previous literature on this topic, our bounds are anytime-valid (i.e., time-uniform), meaning that they hold at all stopping times, not only for a fixed sampl
Externí odkaz:
http://arxiv.org/abs/2302.03421
Entropy regularization is known to improve exploration in sequential decision-making problems. We show that this same mechanism can also lead to nearly unbiased and lower-variance estimates of the mean reward in the optimize-and-estimate structured b
Externí odkaz:
http://arxiv.org/abs/2208.11747
This paper introduces a new, highly consequential setting for the use of computer vision for environmental sustainability. Concentrated Animal Feeding Operations (CAFOs) (aka intensive livestock farms or "factory farms") produce significant manure an
Externí odkaz:
http://arxiv.org/abs/2208.08919
Autor:
Henderson, Peter, Chugg, Ben, Anderson, Brandon, Altenburger, Kristen, Turk, Alex, Guyton, John, Goldin, Jacob, Ho, Daniel E.
We introduce a new setting, optimize-and-estimate structured bandits. Here, a policy must select a batch of arms, each characterized by its own context, that would allow it to both maximize reward and maintain an accurate (ideally unbiased) populatio
Externí odkaz:
http://arxiv.org/abs/2204.11910
Concentrated Animal Feeding Operations (CAFOs) pose serious risks to air, water, and public health, but have proven to be challenging to regulate. The U.S. Government Accountability Office notes that a basic challenge is the lack of comprehensive loc
Externí odkaz:
http://arxiv.org/abs/2112.10988
We explore the promises and challenges of employing sequential decision-making algorithms -- such as bandits, reinforcement learning, and active learning -- in law and public policy. While such algorithms have well-characterized performance in the pr
Externí odkaz:
http://arxiv.org/abs/2112.06833
Autor:
Chugg, Ben, Ho, Daniel E.
In many public health settings, there is a perceived tension between allocating resources to known vulnerable areas and learning about the overall prevalence of the problem. Inspired by a door-to-door Covid-19 testing program we helped design, we com
Externí odkaz:
http://arxiv.org/abs/2110.13306