Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Bahadori, Mohammad Taha"'
Autor:
Fotouhi, Milad, Bahadori, Mohammad Taha, Feyisetan, Oluwaseyi, Arabshahi, Payman, Heckerman, David
We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based approach tha
Externí odkaz:
http://arxiv.org/abs/2408.11852
Autor:
Quintas-Martinez, Victor, Bahadori, Mohammad Taha, Santiago, Eduardo, Mu, Jeff, Janzing, Dominik, Heckerman, David
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024
Comparing two samples of data, we observe a change in the distribution of an outcome variable. In the presence of multiple explanatory variables, how much of the change can be explained by each possible cause? We develop a new estimation strategy tha
Externí odkaz:
http://arxiv.org/abs/2404.08839
We study the problem of observational causal inference with continuous treatments in the framework of inverse propensity-score weighting. To obtain stable weights, we design a new algorithm based on entropy balancing that learns weights to directly m
Externí odkaz:
http://arxiv.org/abs/2107.13068
Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of the concepts
Externí odkaz:
http://arxiv.org/abs/2007.11500
We study the invariance characteristics of pre-trained predictive models by empirically learning transformations on the input that leave the prediction function approximately unchanged. To learn invariant transformations, we minimize the Wasserstein
Externí odkaz:
http://arxiv.org/abs/1911.03295
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a serie
Externí odkaz:
http://arxiv.org/abs/1904.12206
Autor:
Jin, Mengqi, Bahadori, Mohammad Taha, Colak, Aaron, Bhatia, Parminder, Celikkaya, Busra, Bhakta, Ram, Senthivel, Selvan, Khalilia, Mohammed, Navarro, Daniel, Zhang, Borui, Doman, Tiberiu, Ravi, Arun, Liger, Matthieu, Kass-hout, Taha
Clinical text provides essential information to estimate the acuity of a patient during hospital stays in addition to structured clinical data. In this study, we explore how clinical text can complement a clinical predictive learning task. We leverag
Externí odkaz:
http://arxiv.org/abs/1811.12276
Autor:
Bahadori, Mohammad Taha, Chalupka, Krzysztof, Choi, Edward, Chen, Robert, Stewart, Walter F., Sun, Jimeng
In application domains such as healthcare, we want accurate predictive models that are also causally interpretable. In pursuit of such models, we propose a causal regularizer to steer predictive models towards causally-interpretable solutions and the
Externí odkaz:
http://arxiv.org/abs/1702.02604
Deep learning methods exhibit promising performance for predictive modeling in healthcare, but two important challenges remain: -Data insufficiency:Often in healthcare predictive modeling, the sample size is insufficient for deep learning methods to
Externí odkaz:
http://arxiv.org/abs/1611.07012
Autor:
Choi, Edward, Bahadori, Mohammad Taha, Kulas, Joshua A., Schuetz, Andy, Stewart, Walter F., Sun, Jimeng
Accuracy and interpretability are two dominant features of successful predictive models. Typically, a choice must be made in favor of complex black box models such as recurrent neural networks (RNN) for accuracy versus less accurate but more interpre
Externí odkaz:
http://arxiv.org/abs/1608.05745