Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Stangl, Kevin"'
Autor:
Stangl, Kevin
This thesis investigates three areas targeted at improving the reliability of machine learning; fairness in machine learning, strategic classification, and algorithmic robustness. Each of these domains has special properties or structure that can com
Externí odkaz:
http://arxiv.org/abs/2408.16040
Zero-shot anomaly segmentation using pre-trained foundation models is a promising approach that enables effective algorithms without expensive, domain-specific training or fine-tuning. Ensuring that these methods work across various environmental con
Externí odkaz:
http://arxiv.org/abs/2405.07969
In strategic classification, agents modify their features, at a cost, to ideally obtain a positive classification from the learner's classifier. The typical response of the learner is to carefully modify their classifier to be robust to such strategi
Externí odkaz:
http://arxiv.org/abs/2402.08758
We consider the vulnerability of fairness-constrained learning to small amounts of malicious noise in the training data. Konstantinov and Lampert (2021) initiated the study of this question and presented negative results showing there exist data dist
Externí odkaz:
http://arxiv.org/abs/2307.11892
A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example. In contrast, the attacker only needs to find one s
Externí odkaz:
http://arxiv.org/abs/2303.08944
We initiate the study of strategic behavior in screening processes with multiple classifiers. We focus on two contrasting settings: a conjunctive setting in which an individual must satisfy all classifiers simultaneously, and a sequential setting in
Externí odkaz:
http://arxiv.org/abs/2301.13397
Consider an actor making selection decisions using a series of classifiers, which we term a sequential screening process. The early stages filter out some applicants, and in the final stage an expensive but accurate test is applied to the individuals
Externí odkaz:
http://arxiv.org/abs/2203.07513
Autor:
Blum, Avrim, Stangl, Kevin
Multiple fairness constraints have been proposed in the literature, motivated by a range of concerns about how demographic groups might be treated unfairly by machine learning classifiers. In this work we consider a different motivation; learning fro
Externí odkaz:
http://arxiv.org/abs/1912.01094
Publikováno v:
Involve 12 (2019) 97-115
Excited random walks (ERWs) are a self-interacting non-Markovian random walk in which the future behavior of the walk is influenced by the number of times the walk has previously visited its current site. We study the speed of the walk, defined as $V
Externí odkaz:
http://arxiv.org/abs/1707.02969
Compressed sensing (CS) is a new signal acquisition paradigm that enables the reconstruction of signals and images from a low number of samples. A particularly exciting application of CS is Magnetic Resonance Imaging (MRI), where CS significantly spe
Externí odkaz:
http://arxiv.org/abs/1608.04728