1 code implementation • 20 Feb 2024 • Marton Havasi, Sonali Parbhoo, Finale Doshi-Velez
Interpretability methods that utilise local surrogate models (e. g. LIME) are very good at describing the behaviour of the predictive model at a point of interest, but they are not guaranteed to extrapolate to the local region surrounding the point.
no code implementations • 9 Aug 2023 • Leo Benac, Sonali Parbhoo, Finale Doshi-Velez
Offline Reinforcement learning is commonly used for sequential decision-making in domains such as healthcare and education, where the rewards are known and the transition dynamics $T$ must be estimated on the basis of batch data.
1 code implementation • 13 Jul 2023 • Aaman Rebello, Shengpu Tang, Jenna Wiens, Sonali Parbhoo
In this work, we propose a new family of "decomposed" importance sampling (IS) estimators based on factored action spaces.
no code implementations • 20 Jun 2023 • Sarah Rathnam, Sonali Parbhoo, Weiwei Pan, Susan A. Murphy, Finale Doshi-Velez
We demonstrate that planning under a lower discount factor produces an identical optimal policy to planning using any prior on the transition matrix that has the same distribution for all states and actions.
no code implementations • 6 Apr 2023 • Abhishek Sharma, Sonali Parbhoo, Omer Gottesman, Finale Doshi-Velez
Decision-focused (DF) model-based reinforcement learning has recently been introduced as a powerful algorithm that can focus on learning the MDP dynamics that are most relevant for obtaining high returns.
no code implementations • 13 Jan 2023 • Taylor W. Killian, Sonali Parbhoo, Marzyeh Ghassemi
We find that DistDeD significantly improves over prior discovery approaches, providing indications of the risk 10 hours earlier on average as well as increasing detection by 20%.
no code implementations • 13 Jul 2022 • Jiayu Yao, Sonali Parbhoo, Weiwei Pan, Finale Doshi-Velez
We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes.
no code implementations • 20 Jan 2022 • Sonali Parbhoo, Shalmali Joshi, Finale Doshi-Velez
A precise description of the causal estimand highlights which OPE estimands are identifiable from observational data under the stated generative assumptions.
1 code implementation • 25 Nov 2021 • Maxim Samarin, Vitali Nesterov, Mario Wieser, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth
We address these shortcomings with a novel approach to cycle consistency.
no code implementations • 25 Oct 2021 • Abhishek Sharma, Catherine Zeng, Sanjana Narayanan, Sonali Parbhoo, Finale Doshi-Velez
Probabilistic models help us encode latent structures that both model the data and are ideally also useful for specific downstream tasks.
no code implementations • 22 Sep 2021 • Nari Johnson, Sonali Parbhoo, Andrew Slavin Ross, Finale Doshi-Velez
Machine learning models that utilize patient data across time (rather than just the most recent measurements) have increased performance for many risk stratification tasks in the intensive care unit.
no code implementations • 13 Sep 2021 • Shalmali Joshi, Sonali Parbhoo, Finale Doshi-Velez
Our deferral policy is adaptive to the non-stationarity in the dynamics.
no code implementations • 20 Mar 2021 • Sonali Parbhoo, Stefan Bauer, Patrick Schwab
Estimating an individual's potential response to interventions from observational data is of high practical relevance for many domains, such as healthcare, public policy or economics.
no code implementations • 13 Jan 2021 • Melanie F. Pradier, Javier Zazo, Sonali Parbhoo, Roy H. Perlis, Maurizio Zazzi, Finale Doshi-Velez
We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance.
no code implementations • 31 Aug 2020 • Patrick Schwab, Arash Mehrjou, Sonali Parbhoo, Leo Anthony Celi, Jürgen Hetzel, Markus Hofer, Bernhard Schölkopf, Stefan Bauer
Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with rapid human-to-human transmission and a high case fatality rate particularly in older patients.
no code implementations • ICML 2020 • Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo Anthony Celi, Emma Brunskill, Finale Doshi-Velez
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity.
1 code implementation • NeurIPS 2020 • Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, Volker Roth
Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser.
no code implementations • 14 Aug 2019 • Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez
Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts.
no code implementations • 13 Aug 2019 • Mike Wu, Sonali Parbhoo, Michael Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez
The lack of interpretability remains a barrier to the adoption of deep neural networks.
no code implementations • 26 Nov 2018 • Sonali Parbhoo, Mario Wieser, Volker Roth
Estimating the causal effects of an intervention in the presence of confounding is a frequently occurring problem in applications such as medicine.
no code implementations • 19 Nov 2018 • Adam Kortylewski, Mario Wieser, Andreas Morel-Forster, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth, Thomas Vetter
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
no code implementations • 6 Jul 2018 • Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth
Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.
2 code implementations • 16 Nov 2017 • Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez
The lack of interpretability remains a key barrier to the adoption of deep models in many applications.
no code implementations • CVPR 2019 • Adam Kortylewski, Aleksander Wieczorek, Mario Wieser, Clemens Blumer, Sonali Parbhoo, Andreas Morel-Forster, Volker Roth, Thomas Vetter
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.
no code implementations • 6 Oct 2015 • Dinu Kaufmann, Sonali Parbhoo, Aleksander Wieczorek, Sebastian Keller, David Adametz, Volker Roth
This paper considers a Bayesian view for estimating a sub-network in a Markov random field.