104 citations · 144 across the 25 of their papers we have counts for
20 papers · 1 filter
Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories
Leo Benac, Abhishek Sharma, Sonali Parbhoo +1
We consider the problem of estimating the transition dynamics from near-optimal expert trajectories in the context of offline model-based reinforcement learning. We develop a…
Decision-Point Guided Safe Policy Improvement
Abhishek Sharma, Leo Benac, Sonali Parbhoo +1
Within batch reinforcement learning, safe policy improvement (SPI) seeks to ensure that the learnt policy performs at least as well as the behavior policy that generated the datase…
Tree-Based Leakage Inspection and Control in Concept Bottleneck Models
Angelos Ragkousis, Sonali Parbhoo
As AI models grow larger, the demand for accountability and interpretability has become increasingly critical for understanding their decision-making processes. Concept Bottleneck…
Towards Integrating Personal Knowledge into Test-Time Predictions
Isaac Lage, Sonali Parbhoo, Finale Doshi-Velez
Machine learning (ML) models can make decisions based on large amounts of data, but they can be missing personal knowledge available to human users about whom predictions are made.…
Guarantee Regions for Local Explanations
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…
Bayesian Inverse Transition Learning for Offline Settings
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…
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
Sarah Rathnam, Sonali Parbhoo, Weiwei Pan +2
Discount regularization, using a shorter planning horizon when calculating the optimal policy, is a popular choice to restrict planning to a less complex set of policies when estim…
Decision-Focused Model-based Reinforcement Learning for Reward Transfer
Abhishek Sharma, Sonali Parbhoo, Omer Gottesman +1
Model-based reinforcement learning (MBRL) provides a way to learn a transition model of the environment, which can then be used to plan personalized policies for different patient…
Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning
Taylor W. Killian, Sonali Parbhoo, Marzyeh Ghassemi
In safety-critical decision-making scenarios being able to identify worst-case outcomes, or dead-ends is crucial in order to develop safe and reliable policies in practice. These s…
Policy Optimization with Sparse Global Contrastive Explanations
Jiayu Yao, Sonali Parbhoo, Weiwei Pan +1
We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes. Our goal is to make minimal changes while gaini…
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
Sonali Parbhoo, Shalmali Joshi, Finale Doshi-Velez
Assessing the effects of a policy based on observational data from a different policy is a common problem across several high-stake decision-making domains, and several off-policy…
Learning Conditional Invariance through Cycle Consistency
Maxim Samarin, Vitali Nesterov, Mario Wieser +3
Identifying meaningful and independent factors of variation in a dataset is a challenging learning task frequently addressed by means of deep latent variable models. This task can…
On Learning Prediction-Focused Mixtures
Abhishek Sharma, Catherine Zeng, Sanjana Narayanan +2
Probabilistic models help us encode latent structures that both model the data and are ideally also useful for specific downstream tasks. Among these, mixture models and their time…
Learning Predictive and Interpretable Timeseries Summaries from ICU Data
Nari Johnson, Sonali Parbhoo, Andrew Slavin Ross +1
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 i…
Learning-to-defer for sequential medical decision-making under uncertainty
Shalmali Joshi, Sonali Parbhoo, Finale Doshi-Velez
Learning-to-defer is a framework to automatically defer decision-making to a human expert when ML-based decisions are deemed unreliable. Existing learning-to-defer frameworks are n…
NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments
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 economi…
Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible
Melanie F. Pradier, Javier Zazo, Sonali Parbhoo +3
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 predict…
Inverse Learning of Symmetries
Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek +1
Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be…
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Mike Wu, Sonali Parbhoo, Michael C. Hughes +2
Deep models have advanced prediction in many domains, but their lack of interpretability remains a key barrier to the adoption in many real world applications. There exists a large…
Regional Tree Regularization for Interpretability in Black Box Models
Mike Wu, Sonali Parbhoo, Michael Hughes +5
The lack of interpretability remains a barrier to the adoption of deep neural networks. Recently, tree regularization has been proposed to encourage deep neural networks to resembl…