no code implementations • Findings (NAACL) 2022 • Daniel Liebling, Katherine Heller, Samantha Robertson, Wesley Deng
Machine translation models are embedded in larger user-facing systems.
no code implementations • 18 Mar 2024 • Stephen R. Pfohl, Heather Cole-Lewis, Rory Sayres, Darlene Neal, Mercy Asiedu, Awa Dieng, Nenad Tomasev, Qazi Mamunur Rashid, Shekoofeh Azizi, Negar Rostamzadeh, Liam G. McCoy, Leo Anthony Celi, Yun Liu, Mike Schaekermann, Alanna Walton, Alicia Parrish, Chirag Nagpal, Preeti Singh, Akeiylah Dewitt, Philip Mansfield, Sushant Prakash, Katherine Heller, Alan Karthikesalingam, Christopher Semturs, Joelle Barral, Greg Corrado, Yossi Matias, Jamila Smith-Loud, Ivor Horn, Karan Singhal
Large language models (LLMs) hold immense promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities.
no code implementations • 5 Mar 2024 • Mercy Asiedu, Awa Dieng, Iskandar Haykel, Negar Rostamzadeh, Stephen Pfohl, Chirag Nagpal, Maria Nagawa, Abigail Oppong, Sanmi Koyejo, Katherine Heller
Whereas experts generally expressed a shared view about the relevance of colonial history for the development and implementation of AI technologies in Africa, the majority of the general population participants surveyed did not think there was a direct link between AI and colonialism.
no code implementations • 14 Dec 2023 • Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D'Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, Peter Shaw, Jonathan Berant
However, even pretrain reward ensembles do not eliminate reward hacking: we show several qualitative reward hacking phenomena that are not mitigated by ensembling because all reward models in the ensemble exhibit similar error patterns.
no code implementations • 29 Sep 2023 • Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs).
no code implementations • 2 Jun 2023 • Eltayeb Ahmed, Diana Mincu, Lauren Harrell, Katherine Heller, Subhrajit Roy
We demonstrate the benefits of STUDY in the recommendation of books for students who are dyslexic, or struggling readers.
no code implementations • 5 Apr 2023 • Mercy Nyamewaa Asiedu, Awa Dieng, Abigail Oppong, Maria Nagawa, Sanmi Koyejo, Katherine Heller
With growing machine learning (ML) applications in healthcare, there have been calls for fairness in ML to understand and mitigate ethical concerns these systems may pose.
no code implementations • 15 Feb 2023 • Alexander Norcliffe, Lev Proleev, Diana Mincu, Fletcher Lee Hartsell, Katherine Heller, Subhrajit Roy
Multiple sclerosis is a disease that affects the brain and spinal cord, it can lead to severe disability and has no known cure.
no code implementations • 11 May 2022 • Ben Hutchinson, Negar Rostamzadeh, Christina Greer, Katherine Heller, Vinodkumar Prabhakaran
Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and responsibilities.
no code implementations • 8 Apr 2022 • Subhrajit Roy, Diana Mincu, Lev Proleev, Negar Rostamzadeh, Chintan Ghate, Natalie Harris, Christina Chen, Jessica Schrouff, Nenad Tomasev, Fletcher Lee Hartsell, Katherine Heller
To the best of our knowledge, our results are the first to show that it is possible to predict disease progression using POMs and demographic data in the context of both clinical trials and smartphone-base studies by using two datasets.
1 code implementation • 26 Feb 2022 • Negar Rostamzadeh, Diana Mincu, Subhrajit Roy, Andrew Smart, Lauren Wilcox, Mahima Pushkarna, Jessica Schrouff, Razvan Amironesei, Nyalleng Moorosi, Katherine Heller
Our findings from the interviewee study and case studies show 1) that datasheets should be contextualized for healthcare, 2) that despite incentives to adopt accountability practices such as datasheets, there is a lack of consistency in the broader use of these practices 3) how the ML for health community views datasheets and particularly \textit{Healthsheets} as diagnostic tool to surface the limitations and strength of datasets and 4) the relative importance of different fields in the datasheet to healthcare concerns.
no code implementations • 2 Feb 2022 • Jessica Schrouff, Natalie Harris, Oluwasanmi Koyejo, Ibrahim Alabdulmohsin, Eva Schnider, Krista Opsahl-Ong, Alex Brown, Subhrajit Roy, Diana Mincu, Christina Chen, Awa Dieng, YuAn Liu, Vivek Natarajan, Alan Karthikesalingam, Katherine Heller, Silvia Chiappa, Alexander D'Amour
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings.
5 code implementations • 16 Jan 2021 • Chirag Nagpal, Steve Yadlowsky, Negar Rostamzadeh, Katherine Heller
Survival analysis is a challenging variation of regression modeling because of the presence of censoring, where the outcome measurement is only partially known, due to, for example, loss to follow up.
no code implementations • 6 Nov 2020 • Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, D. Sculley
Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains.
1 code implementation • ICML 2020 • Michael W. Dusenberry, Ghassen Jerfel, Yeming Wen, Yi-An Ma, Jasper Snoek, Katherine Heller, Balaji Lakshminarayanan, Dustin Tran
Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning.
no code implementations • 13 Nov 2019 • Stephen R. Pfohl, Andrew M. Dai, Katherine Heller
The use of collaborative and decentralized machine learning techniques such as federated learning have the potential to enable the development and deployment of clinical risk predictions models in low-resource settings without requiring sensitive data be shared or stored in a central repository.
1 code implementation • 10 Jun 2019 • Michael W. Dusenberry, Dustin Tran, Edward Choi, Jonas Kemp, Jeremy Nixon, Ghassen Jerfel, Katherine Heller, Andrew M. Dai
We further show that RNNs with only Bayesian embeddings can be a more efficient way to capture model uncertainty compared to ensembles, and we analyze how model uncertainty is impacted across individual input features and patient subgroups.
no code implementations • ICLR 2019 • Erin Grant, Ghassen Jerfel, Katherine Heller, Thomas L. Griffiths
Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task.
no code implementations • NeurIPS 2019 • Ghassen Jerfel, Erin Grant, Thomas L. Griffiths, Katherine Heller
Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task.
1 code implementation • 24 Jul 2018 • Elizabeth Lorenzi, Ricardo Henao, Katherine Heller
We develop a hierarchical infinite latent factor model (HIFM) to appropriately account for the covariance structure across subpopulations in data.
Applications
no code implementations • ICLR 2018 • Joseph Futoma, Anthony Lin, Mark Sendak, Armando Bedoya, Meredith Clement, Cara O'Brien, Katherine Heller
We evaluate our approach on a heterogeneous dataset of septic spanning 15 months from our university health system, and find that our learned policy could reduce patient mortality by as much as 8. 2\% from an overall baseline mortality rate of 13. 3\%.
no code implementations • 1 Dec 2017 • Kai Fan, Qi Wei, Wenlin Wang, Amit Chakraborty, Katherine Heller
We propose a new method that uses deep learning techniques to solve the inverse problems.
no code implementations • 19 Aug 2017 • Joseph Futoma, Sanjay Hariharan, Mark Sendak, Nathan Brajer, Meredith Clement, Armando Bedoya, Cara O'Brien, Katherine Heller
Latent function values from the Gaussian process are then fed into a deep recurrent neural network to classify patient encounters as septic or not, and the overall model is trained end-to-end using back-propagation.
2 code implementations • ICML 2017 • Joseph Futoma, Sanjay Hariharan, Katherine Heller
We present a scalable end-to-end classifier that uses streaming physiological and medication data to accurately predict the onset of sepsis, a life-threatening complication from infections that has high mortality and morbidity.
no code implementations • 16 Aug 2016 • Joseph Futoma, Mark Sendak, C. Blake Cameron, Katherine Heller
Prediction of the future trajectory of a disease is an important challenge for personalized medicine and population health management.
no code implementations • 13 Nov 2015 • Kai Fan, Katherine Heller
Specifically, we propose a Stochastic SMC algorithm which initializes the set of $k$ means, providing the initial centers chosen from the collapsed particles.
no code implementations • 9 Sep 2015 • Kai Fan, Ziteng Wang, Jeff Beck, James Kwok, Katherine Heller
We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well.
no code implementations • 11 Nov 2014 • Fangjian Guo, Charles Blundell, Hanna Wallach, Katherine Heller
We present the Bayesian Echo Chamber, a new Bayesian generative model for social interaction data.
no code implementations • 28 Dec 2009 • Ricardo Silva, Katherine Heller, Zoubin Ghahramani, Edoardo M. Airoldi
Our work addresses the following question: is the relation between objects A and B analogous to those relations found in $\mathbf{S}$?