2 code implementations • 9 Apr 2024 • Sebastian Bordt, Harsha Nori, Vanessa Rodrigues, Besmira Nushi, Rich Caruana
We then compare the few-shot learning performance of LLMs on datasets that were seen during training to the performance on datasets released after training.
1 code implementation • 11 Mar 2024 • Sebastian Bordt, Harsha Nori, Rich Caruana
While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over.
1 code implementation • 22 Feb 2024 • Sebastian Bordt, Ben Lengerich, Harsha Nori, Rich Caruana
Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans.
1 code implementation • 30 Jan 2024 • Chandan Singh, Jeevana Priya Inala, Michel Galley, Rich Caruana, Jianfeng Gao
We highlight two emerging research priorities for LLM interpretation: using LLMs to directly analyze new datasets and to generate interactive explanations.
no code implementations • 22 Nov 2023 • Odelia Melamed, Rich Caruana
Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions.
no code implementations • 16 Oct 2023 • Tomas M. Bosschieter, Zifei Xu, Hui Lan, Benjamin J. Lengerich, Harsha Nori, Ian Painter, Vivienne Souter, Rich Caruana
The interpretability of the EBM models reveals surprising insights into the features contributing to risk (e. g. maternal height is the second most important feature for shoulder dystocia) and may have potential for clinical application in the prediction and prevention of serious complications in pregnancy.
1 code implementation • 2 Aug 2023 • Benjamin J. Lengerich, Sebastian Bordt, Harsha Nori, Mark E. Nunnally, Yin Aphinyanaphongs, Manolis Kellis, Rich Caruana
We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components.
no code implementations • 29 Jun 2023 • Alexander Peysakhovich, Rich Caruana, Yin Aphinyanaphongs
We consider a patient risk models which has access to patient features such as vital signs, lab values, and prior history but does not have access to a patient's diagnosis.
no code implementations • 25 May 2023 • Daniel Schug, Sai Yerramreddy, Rich Caruana, Craig Greenberg, Justyna P. Zwolak
As the deployment of computer vision technology becomes increasingly common in science, the need for explanations of the system and its output has become a focus of great concern.
no code implementations • 23 Apr 2023 • Zhi Chen, Sarah Tan, Urszula Chajewska, Cynthia Rudin, Rich Caruana
Missing values are a fundamental problem in data science.
1 code implementation • 27 Feb 2023 • Zijie J. Wang, Jennifer Wortman Vaughan, Rich Caruana, Duen Horng Chau
Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed.
no code implementations • 15 Nov 2022 • Benjamin Lengerich, Mark E. Nunnally, Yin Aphinyanaphongs, Rich Caruana
Treatment protocols, disease understanding, and viral characteristics changed over the course of the COVID-19 pandemic; as a result, the risks associated with patient comorbidities and biomarkers also changed.
4 code implementations • 23 Sep 2022 • Chandan Singh, Armin Askari, Rich Caruana, Jianfeng Gao
Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks.
no code implementations • 12 Jul 2022 • Tomas M. Bosschieter, Zifei Xu, Hui Lan, Benjamin J. Lengerich, Harsha Nori, Kristin Sitcov, Vivienne Souter, Rich Caruana
Most pregnancies and births result in a good outcome, but complications are not uncommon and when they do occur, they can be associated with serious implications for mothers and babies.
2 code implementations • 30 Jun 2022 • Zijie J. Wang, Alex Kale, Harsha Nori, Peter Stella, Mark E. Nunnally, Duen Horng Chau, Mihaela Vorvoreanu, Jennifer Wortman Vaughan, Rich Caruana
Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed.
1 code implementation • 22 Feb 2022 • Fengshi Niu, Harsha Nori, Brian Quistorff, Rich Caruana, Donald Ngwe, Aadharsh Kannan
Our meta-algorithm can work with simple, single-stage CATE estimators such as S-learner and more complex multi-stage estimators such as DR and R-learner.
1 code implementation • 6 Dec 2021 • Zijie J. Wang, Alex Kale, Harsha Nori, Peter Stella, Mark Nunnally, Duen Horng Chau, Mihaela Vorvoreanu, Jennifer Wortman Vaughan, Rich Caruana
Recent strides in interpretable machine learning (ML) research reveal that models exploit undesirable patterns in the data to make predictions, which potentially causes harms in deployment.
no code implementations • 28 Oct 2021 • Chun-Hao Chang, George Alexandru Adam, Rich Caruana, Anna Goldenberg
Although reinforcement learning (RL) has tremendous success in many fields, applying RL to real-world settings such as healthcare is challenging when the reward is hard to specify and no exploration is allowed.
1 code implementation • 17 Jun 2021 • Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan Kulkarni
We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy.
2 code implementations • ICLR 2022 • Chun-Hao Chang, Rich Caruana, Anna Goldenberg
Deployment of machine learning models in real high-risk settings (e. g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability.
no code implementations • 9 Feb 2021 • Jonathan A. Weyn, Dale R. Durran, Rich Caruana, Nathaniel Cresswell-Clay
Current forecast systems have low skill in predicting one- or 2-week-average weather patterns at S2S time scales.
no code implementations • 28 Sep 2020 • Ben Lengerich, Eric Xing, Rich Caruana
Conversely, the probability of an interaction of $k$ variables surviving Dropout at rate $p$ is $\mathcal{O}((1-p)^k)$.
no code implementations • 2 Jul 2020 • Benjamin Lengerich, Eric P. Xing, Rich Caruana
We examine Dropout through the perspective of interactions.
2 code implementations • 11 Jun 2020 • Chun-Hao Chang, Sarah Tan, Ben Lengerich, Anna Goldenberg, Rich Caruana
Generalized additive models (GAMs) have become a leading modelclass for interpretable machine learning.
6 code implementations • NeurIPS 2021 • Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, Ben Lengerich, Rich Caruana, Geoffrey Hinton
They perform similarly to existing state-of-the-art generalized additive models in accuracy, but are more flexible because they are based on neural nets instead of boosted trees.
1 code implementation • 15 Mar 2020 • Jonathan A. Weyn, Dale R. Durran, Rich Caruana
The cubed-sphere remapping minimizes the distortion on the cube faces on which convolution operations are performed and provides natural boundary conditions for padding in the CNN.
1 code implementation • 12 Nov 2019 • Benjamin Lengerich, Sarah Tan, Chun-Hao Chang, Giles Hooker, Rich Caruana
Models which estimate main effects of individual variables alongside interaction effects have an identifiability challenge: effects can be freely moved between main effects and interaction effects without changing the model prediction.
2 code implementations • 19 Sep 2019 • Harsha Nori, Samuel Jenkins, Paul Koch, Rich Caruana
InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers.
2 code implementations • NeurIPS 2019 • Hanzhang Hu, John Langford, Rich Caruana, Saurajit Mukherjee, Eric Horvitz, Debadeepta Dey
We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers.
1 code implementation • 22 Oct 2018 • Xuezhou Zhang, Sarah Tan, Paul Koch, Yin Lou, Urszula Chajewska, Rich Caruana
In the first part of this paper, we generalize a state-of-the-art GAM learning algorithm based on boosted trees to the multiclass setting, and show that this multiclass algorithm outperforms existing GAM learning algorithms and sometimes matches the performance of full complexity models such as gradient boosted trees.
1 code implementation • ICLR 2019 • Sarah Tan, Giles Hooker, Paul Koch, Albert Gordo, Rich Caruana
In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based explanations.
no code implementations • 27 Nov 2017 • Andrew Gordon Wilson, Jason Yosinski, Patrice Simard, Rich Caruana, William Herlands
This is the Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning, held in Long Beach, California, USA on December 7, 2017
1 code implementation • 17 Oct 2017 • Sarah Tan, Rich Caruana, Giles Hooker, Yin Lou
We compare the student model trained with distillation to a second un-distilled transparent model trained on ground-truth outcomes, and use differences between the two models to gain insight into the black-box model.
no code implementations • 4 Jul 2017 • Himabindu Lakkaraju, Ece Kamar, Rich Caruana, Jure Leskovec
To the best of our knowledge, this is the first approach which can produce global explanations of the behavior of any given black box model through joint optimization of unambiguity, fidelity, and interpretability, while also allowing users to explore model behavior based on their preferences.
no code implementations • 28 Oct 2016 • Himabindu Lakkaraju, Ece Kamar, Rich Caruana, Eric Horvitz
Predictive models deployed in the real world may assign incorrect labels to instances with high confidence.
no code implementations • CVPR 2016 • Jia-Bin Huang, Rich Caruana, Andrew Farnsworth, Steve Kelling, Narendra Ahuja
In this paper, we present a vision-based system for detecting migrating birds in flight at night.
no code implementations • 2 Feb 2016 • Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana
A fundamental goal of search engines is to identify, given a query, documents that have relevant text.
no code implementations • 19 Nov 2015 • Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson, Charles Sutton
We consider whether deep convolutional networks (CNNs) can represent decision functions with similar accuracy as recurrent networks such as LSTMs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 17 Jul 2014 • Yin Lou, Jacob Bien, Rich Caruana, Johannes Gehrke
Thus, to make a GPLAM a viable approach in situations in which little is known $a~priori$ about the features, one must overcome two primary model selection challenges: deciding which features to include in the model and determining which of these features to treat nonlinearly.
2 code implementations • NeurIPS 2014 • Lei Jimmy Ba, Rich Caruana
Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision.
no code implementations • NeurIPS 2013 • Jason D. Lee, Ran Gilad-Bachrach, Rich Caruana
In the mixture models problem it is assumed that there are $K$ distributions $\theta_{1},\ldots,\theta_{K}$ and one gets to observe a sample from a mixture of these distributions with unknown coefficients.