Zobrazeno 1 - 10
of 451
pro vyhledávání: '"Roth, Aaron"'
Autor:
Bertran, Martin, Tang, Shuai, Kearns, Michael, Morgenstern, Jamie, Roth, Aaron, Wu, Zhiwei Steven
Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show that, count
Externí odkaz:
http://arxiv.org/abs/2405.20272
There is a long history in machine learning of model ensembling, beginning with boosting and bagging and continuing to the present day. Much of this history has focused on combining models for classification and regression, but recently there is inte
Externí odkaz:
http://arxiv.org/abs/2405.16752
Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, both theoretically (where worst-case sample and computational complexities must scale with state space cardinality) and experimentally (where function approxima
Externí odkaz:
http://arxiv.org/abs/2405.16739
This paper introduces a framework for post-processing machine learning models so that their predictions satisfy multi-group fairness guarantees. Based on the celebrated notion of multicalibration, we introduce $(\mathbf{s},\mathcal{G}, \alpha)-$GMC (
Externí odkaz:
http://arxiv.org/abs/2405.02225
This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously across variou
Externí odkaz:
http://arxiv.org/abs/2404.04689
We study a repeated contracting setting in which a Principal adaptively chooses amongst $k$ Agents at each of $T$ rounds. The Agents are non-myopic, and so a mechanism for the Principal induces a $T$-round extensive form game amongst the Agents. We g
Externí odkaz:
http://arxiv.org/abs/2402.17108
Blasiok et al. [2023] proposed distance to calibration as a natural measure of calibration error that unlike expected calibration error (ECE) is continuous. Recently, Qiao and Zheng [2024] gave a non-constructive argument establishing the existence o
Externí odkaz:
http://arxiv.org/abs/2402.11410
Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accurate model, as measured by overall error on a holdout set, and it is c
Externí odkaz:
http://arxiv.org/abs/2402.10795
Autor:
Roth, Aaron, Shi, Mirah
We study the problem of making predictions so that downstream agents who best respond to them will be guaranteed diminishing swap regret, no matter what their utility functions are. It has been known since Foster and Vohra (1997) that agents who best
Externí odkaz:
http://arxiv.org/abs/2402.08753
Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a privacy vulner
Externí odkaz:
http://arxiv.org/abs/2312.05140