Zobrazeno 1 - 10
of 177
pro vyhledávání: '"Bastani, Osbert"'
Conformal prediction has recently emerged as a promising strategy for quantifying the uncertainty of a predictive model; these algorithms modify the model to output sets of labels that are guaranteed to contain the true label with high probability. H
Externí odkaz:
http://arxiv.org/abs/2410.06296
Autor:
Yao, Michael S., Chae, Allison, Kahn Jr., Charles E., Witschey, Walter R., Gee, James C., Sagreiya, Hersh, Bastani, Osbert
Diagnostic imaging studies are an increasingly important component of the workup and management of acutely presenting patients. However, ordering appropriate imaging studies according to evidence-based medical guidelines is a challenging task with a
Externí odkaz:
http://arxiv.org/abs/2409.19177
The capability to generate diverse text is a key challenge facing large language models (LLMs). Thus far, diversity has been studied via metrics such as $n$-gram diversity or diversity of BERT embeddings. However, for these kinds of diversity, the us
Externí odkaz:
http://arxiv.org/abs/2408.06186
Autor:
Bastani, Osbert
We prove convergence guarantees for generalized low-rank matrix sensing -- i.e., where matrix sensing where the observations may be passed through some nonlinear link function. We focus on local convergence of the optimal estimator, ignoring question
Externí odkaz:
http://arxiv.org/abs/2407.10238
Autor:
Guo, Wentao, Long, Jikai, Zeng, Yimeng, Liu, Zirui, Yang, Xinyu, Ran, Yide, Gardner, Jacob R., Bastani, Osbert, De Sa, Christopher, Yu, Xiaodong, Chen, Beidi, Xu, Zhaozhuo
Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, the application of ZO fine-tuning in memory-constrained settings such as mobile phones and laptops is still challe
Externí odkaz:
http://arxiv.org/abs/2406.02913
Autor:
Ma, Yecheng Jason, Liang, William, Wang, Hung-Ju, Wang, Sam, Zhu, Yuke, Fan, Linxi, Bastani, Osbert, Jayaraman, Dinesh
Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulatio
Externí odkaz:
http://arxiv.org/abs/2406.01967
The growing safety concerns surrounding Large Language Models (LLMs) raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints throu
Externí odkaz:
http://arxiv.org/abs/2405.19544
Machine learning has become an effective tool for automatically annotating unstructured data (e.g., images) with structured labels (e.g., object detections). As a result, a new programming paradigm called neurosymbolic programming has emerged where u
Externí odkaz:
http://arxiv.org/abs/2405.15912
Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label with high
Externí odkaz:
http://arxiv.org/abs/2405.13268
Large language models (LLMs) have shown impressive results at a wide-range of tasks. However, they have limitations, such as hallucinating facts and struggling with arithmetic. Recent work has addressed these issues with sophisticated decoding techni
Externí odkaz:
http://arxiv.org/abs/2405.11361