
Preferential MixtureofExperts: Interpretable Models that Rely on Human Expertise as much as Possible
We propose Preferential MoE, a novel humanML mixtureofexperts model t...
read it

Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment
Many batch RL health applications first discretize time into fixed inter...
read it

Artificial Intelligence Cooperation
The rise of Artificial Intelligence (AI) will bring with it an everincr...
read it

Learning Interpretable ConceptBased Models with Human Feedback
Machine learning models that first learn a representation of a domain in...
read it

Incorporating Interpretable Output Constraints in Bayesian Neural Networks
Domains where supervised models are deployed often come with taskspecif...
read it

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
Variational Autoencoders (VAEs) are deep generative latent variable mod...
read it

BaCOUn: Bayesian Classifers with OutofDistribution Uncertainty
Traditional training of deep classifiers yields overconfident models tha...
read it

Modelbased Reinforcement Learning for SemiMarkov Decision Processes with Neural ODEs
We present two elegant solutions for modeling continuoustime dynamics, ...
read it

Learned UncertaintyAware (LUNA) Bases for Bayesian Regression using MultiHeaded Auxiliary Networks
Neural Linear Models (NLM) are deep models that produce predictive uncer...
read it

PAC Bounds for Imitation and Modelbased Batch Learning of Contextual Markov Decision Processes
We consider the problem of batch multitask reinforcement learning with ...
read it

Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of DuelDDQN for Sepsis Treatment
The potential of Reinforcement Learning (RL) has been demonstrated throu...
read it

PowerConstrained Bandits
Contextual bandits often provide simple and effective personalization in...
read it

Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
Variational Autoencoders (VAEs) are deep generative latent variable mod...
read it

Interpretable OffPolicy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
Offpolicy evaluation in reinforcement learning offers the chance of usi...
read it

POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning
Many medical decisionmaking settings can be framed as partially observe...
read it

Identifying Distinct, Effective Treatments for Acute Hypotension with SODARL: Safely Optimized Diverse Accurate Reinforcement Learning
Hypotension in critical care settings is a lifethreatening emergency th...
read it

Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks
While Bayesian neural networks have many appealing characteristics, curr...
read it

Prediction Focused Topic Models for Electronic Health Records
Electronic Health Record (EHR) data can be represented as discrete count...
read it

Ensembles of Locally Independent Prediction Models
Many ensemble methods encourage their constituent models to be diverse, ...
read it

Learning Deep Bayesian Latent Variable Regression Models that Generalize: When Nonidentifiability is a Problem
Bayesian Neural Networks with Latent Variables (BNN+LV's) provide uncert...
read it

Prediction Focused Topic Models via Vocab Selection
Supervised topic models are often sought to balance prediction quality a...
read it

Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Deep models have advanced prediction in many domains, but their lack of ...
read it

Regional Tree Regularization for Interpretability in Black Box Models
The lack of interpretability remains a barrier to the adoption of deep n...
read it

Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Bayesian Neural Networks (BNNs) place priors over the parameters in a ne...
read it

DiversityInducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies
Standard reinforcement learning methods aim to master one way of solving...
read it

Exploring Computational User Models for Agent Policy Summarization
AI agents are being developed to support high stakes decisionmaking pro...
read it

Defining Admissible Rewards for High Confidence Policy Evaluation
A key impediment to reinforcement learning (RL) in real applications wit...
read it

A general method for regularizing tensor decomposition methods via pseudodata
Tensor decomposition methods allow us to learn the parameters of latent ...
read it

OutputConstrained Bayesian Neural Networks
Bayesian neural network (BNN) priors are defined in parameter space, mak...
read it

Combining Parametric and Nonparametric Models for OffPolicy Evaluation
We consider a modelbased approach to perform batch offpolicy evaluatio...
read it

Truly Batch Apprenticeship Learning with Deep Successor Features
We introduce a novel apprenticeship learning algorithm to learn an exper...
read it

An Evaluation of the HumanInterpretability of Explanation
Recent years have seen a boom in interest in machine learning systems th...
read it

Improving Sepsis Treatment Strategies by Combining Deep and KernelBased Reinforcement Learning
Sepsis is the leading cause of mortality in the ICU. It is challenging t...
read it

Latent Projection BNNs: Avoiding weightspace pathologies by learning latent representations of neural network weights
While modern neural networks are making remarkable gains in terms of pre...
read it

Depthbounding is effective: Improvements and evaluation of unsupervised PCFG induction
There have been several recent attempts to improve the accuracy of gramm...
read it

Behaviour Policy Estimation in OffPolicy Policy Evaluation: Calibration Matters
In this work, we consider the problem of estimating a behaviour policy f...
read it

Learning Qualitatively Diverse and Interpretable Rules for Classification
There has been growing interest in developing accurate models that can a...
read it

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Bayesian Neural Networks (BNNs) have recently received increasing attent...
read it

Evaluating Reinforcement Learning Algorithms in Observational Health Settings
Much attention has been devoted recently to the development of machine l...
read it

HumanintheLoop Interpretability Prior
We often desire our models to be interpretable as well as accurate. Prio...
read it

Representation Balancing MDPs for OffPolicy Policy Evaluation
We study the problem of offpolicy policy evaluation (OPPE) in RL. In co...
read it

A particlebased variational approach to Bayesian Nonnegative Matrix Factorization
Bayesian Nonnegative Matrix Factorization (NMF) is a promising approach...
read it

Unsupervised Grammar Induction with Depthbounded PCFG
There has been recent interest in applying cognitively or empirically mo...
read it

How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the HumanInterpretability of Explanation
Recent years have seen a boom in interest in machine learning systems th...
read it

PredictionConstrained Topic Models for Antidepressant Recommendation
Supervisory signals can help topic models discover lowdimensional data ...
read it

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
Deep neural networks have proven remarkably effective at solving many cl...
read it

Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
The lack of interpretability remains a key barrier to the adoption of de...
read it

Accountability of AI Under the Law: The Role of Explanation
The ubiquity of systems using artificial intelligence or "AI" has brough...
read it

Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems
Bayesian neural networks (BNNs) with latent variables are probabilistic ...
read it

Weighted Tensor Decomposition for Learning Latent Variables with Partial Data
Tensor decomposition methods are popular tools for learning latent varia...
read it
Finale DoshiVelez
is this you? claim profile
Assistant Professor of Computer Science at Harvard Paulson School of Engineering and Applied Sciences, Harvard University, MSc from the University of Cambridge as a Marshall Scholar, her PhD from MIT, and her postdoc at Harvard Medical School.