Zobrazeno 1 - 10
of 933
pro vyhledávání: '"A. Haghtalab"'
A canonical desideratum for prediction problems is that performance guarantees should hold not just on average over the population, but also for meaningful subpopulations within the overall population. But what constitutes a meaningful subpopulation?
Externí odkaz:
http://arxiv.org/abs/2410.14588
The content selection problem of digital services is often modeled as a decision-process where a service chooses, over multiple rounds, an arm to pull from a set of arms that each return a certain reward. This classical model does not account for the
Externí odkaz:
http://arxiv.org/abs/2410.13108
When learning in strategic environments, a key question is whether agents can overcome uncertainty about their preferences to achieve outcomes they could have achieved absent any uncertainty. Can they do this solely through interactions with each oth
Externí odkaz:
http://arxiv.org/abs/2408.08272
We initiate the study of the truthfulness of calibration measures in sequential prediction. A calibration measure is said to be truthful if the forecaster (approximately) minimizes the expected penalty by predicting the conditional expectation of the
Externí odkaz:
http://arxiv.org/abs/2407.13979
Autor:
Halawi, Danny, Wei, Alexander, Wallace, Eric, Wang, Tony T., Haghtalab, Nika, Steinhardt, Jacob
Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we
Externí odkaz:
http://arxiv.org/abs/2406.20053
Autor:
Haghtalab, Nika1 (AUTHOR) nhaghtal@gmail.com, Roughgarden, Tim2 (AUTHOR) tim.roughgarden@gmail.com, Shetty, Abhishek1 (AUTHOR) shetty@berkeley.edu
Publikováno v:
Journal of the ACM. Jun2024, Vol. 71 Issue 3, p1-34. 34p.
Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum et al., 202
Externí odkaz:
http://arxiv.org/abs/2402.15169
A common explanation for negative user impacts of content recommender systems is misalignment between the platform's objective and user welfare. In this work, we show that misalignment in the platform's objective is not the only potential cause of un
Externí odkaz:
http://arxiv.org/abs/2401.05304
A fundamental shortcoming of the concept of Nash equilibrium is its computational intractability: approximating Nash equilibria in normal-form games is PPAD-hard. In this paper, inspired by the ideas of smoothed analysis, we introduce a relaxed varia
Externí odkaz:
http://arxiv.org/abs/2309.12226
Motivated by the emergence of decentralized machine learning (ML) ecosystems, we study the delegation of data collection. Taking the field of contract theory as our starting point, we design optimal and near-optimal contracts that deal with two funda
Externí odkaz:
http://arxiv.org/abs/2309.01837