Zobrazeno 1 - 10
of 2 015
pro vyhledávání: '"Wu, Zhiwei"'
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of targeted rele
Externí odkaz:
http://arxiv.org/abs/2406.13356
We study a multi-agent imitation learning (MAIL) problem where we take the perspective of a learner attempting to coordinate a group of agents based on demonstrations of an expert doing so. Most prior work in MAIL essentially reduces the problem to m
Externí odkaz:
http://arxiv.org/abs/2406.04219
Estimates of causal parameters such as conditional average treatment effects and conditional quantile treatment effects play an important role in real-world decision making. Given this importance, one should ensure these estimators are calibrated. Wh
Externí odkaz:
http://arxiv.org/abs/2406.01933
We establish a new model-agnostic optimization framework for out-of-distribution generalization via multicalibration, a criterion that ensures a predictor is calibrated across a family of overlapping groups. Multicalibration is shown to be associated
Externí odkaz:
http://arxiv.org/abs/2406.00661
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
We consider the problem of model multiplicity in downstream decision-making, a setting where two predictive models of equivalent accuracy cannot agree on the best-response action for a downstream loss function. We show that even when the two predicti
Externí odkaz:
http://arxiv.org/abs/2405.19667
Predictive models are often introduced to decision-making tasks under the rationale that they improve performance over an existing decision-making policy. However, it is challenging to compare predictive performance against an existing decision-makin
Externí odkaz:
http://arxiv.org/abs/2404.00848
Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals who have diverse viewpoints that may conflict with each other. Our work
Externí odkaz:
http://arxiv.org/abs/2403.05006
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations of finetuning to upda
Externí odkaz:
http://arxiv.org/abs/2403.03329
The tension between persuasion and privacy preservation is common in real-world settings. Online platforms should protect the privacy of web users whose data they collect, even as they seek to disclose information about these data to selling advertis
Externí odkaz:
http://arxiv.org/abs/2402.15872