Search Results for author: Finale Doshi-Velez

Found 124 papers, 32 papers with code

Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition

no code implementations CL (ACL) 2021 Lifeng Jin, Lane Schwartz, Finale Doshi-Velez, Timothy Miller, William Schuler

Abstract This article describes a simple PCFG induction model with a fixed category domain that predicts a large majority of attested constituent boundaries, and predicts labels consistent with nearly half of attested constituent labels on a standard evaluation data set of child-directed speech.

Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders

no code implementations13 Mar 2024 Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

It approximates the posterior of the true model a priori; fixing this posterior approximation, we then maximize the lower bound relative to only the generative model.

Density Estimation

Guarantee Regions for Local Explanations

1 code implementation20 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.

Non-Stationary Latent Auto-Regressive Bandits

1 code implementation5 Feb 2024 Anna L. Trella, Walter Dempsey, Finale Doshi-Velez, Susan A. Murphy

We consider the stochastic multi-armed bandit problem with non-stationary rewards.

Semi-parametric Expert Bayesian Network Learning with Gaussian Processes and Horseshoe Priors

no code implementations29 Jan 2024 Yidou Weng, Finale Doshi-Velez

This paper proposes a model learning Semi-parametric rela- tionships in an Expert Bayesian Network (SEBN) with linear parameter and structure constraints.

Gaussian Processes

Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks

no code implementations26 Jan 2024 Eura Nofshin, Siddharth Swaroop, Weiwei Pan, Susan Murphy, Finale Doshi-Velez

Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification.

Attribute

Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping

no code implementations15 Dec 2023 Lauren H. Cooke, Harvey Klyne, Edwin Zhang, Cassidy Laidlaw, Milind Tambe, Finale Doshi-Velez

Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems.

reinforcement-learning Reinforcement Learning (RL)

Why do universal adversarial attacks work on large language models?: Geometry might be the answer

no code implementations1 Sep 2023 Varshini Subhash, Anna Bialas, Weiwei Pan, Finale Doshi-Velez

We believe this new geometric perspective on the underlying mechanism driving universal attacks could help us gain deeper insight into the internal workings and failure modes of LLMs, thus enabling their mitigation.

Dimensionality Reduction

Bayesian Inverse Transition Learning for Offline Settings

no code implementations9 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.

Decision Making

SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text

no code implementations28 Jul 2023 Charumathi Badrinath, Weiwei Pan, Finale Doshi-Velez

A common way to explore text corpora is through low-dimensional projections of the documents, where one hopes that thematically similar documents will be clustered together in the projected space.

Dimensionality Reduction

On the Effective Horizon of Inverse Reinforcement Learning

no code implementations13 Jul 2023 Yiqing Xu, Finale Doshi-Velez, David Hsu

Inverse reinforcement learning (IRL) algorithms often rely on (forward) reinforcement learning or planning over a given time horizon to compute an approximately optimal policy for a hypothesized reward function and then match this policy with expert demonstrations.

Computational Efficiency reinforcement-learning

The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning

no code implementations20 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.

Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare

2 code implementations2 May 2023 Shengpu Tang, Maggie Makar, Michael W. Sjoding, Finale Doshi-Velez, Jenna Wiens

We study the theoretical properties of our approach, identifying scenarios where it is guaranteed to lead to zero bias when used to approximate the Q-function.

Offline RL reinforcement-learning +1

Decision-Focused Model-based Reinforcement Learning for Reward Transfer

no code implementations6 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.

Model-based Reinforcement Learning reinforcement-learning

Modeling Mobile Health Users as Reinforcement Learning Agents

no code implementations1 Dec 2022 Eura Shin, Siddharth Swaroop, Weiwei Pan, Susan Murphy, Finale Doshi-Velez

Mobile health (mHealth) technologies empower patients to adopt/maintain healthy behaviors in their daily lives, by providing interventions (e. g. push notifications) tailored to the user's needs.

Decision Making reinforcement-learning +1

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

no code implementations16 Nov 2022 Jiayu Yao, Yaniv Yacoby, Beau Coker, Weiwei Pan, Finale Doshi-Velez

Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in the finite-width case is intractable.

(When) Are Contrastive Explanations of Reinforcement Learning Helpful?

no code implementations14 Nov 2022 Sanjana Narayanan, Isaac Lage, Finale Doshi-Velez

We find that complete explanations are generally more effective when they are the same size or smaller than a contrastive explanation of the same policy, and no worse when they are larger.

reinforcement-learning Reinforcement Learning (RL)

What Makes a Good Explanation?: A Harmonized View of Properties of Explanations

no code implementations10 Nov 2022 Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, Finale Doshi-Velez

In this work, we survey properties defined in interpretable machine learning papers, synthesize them based on what they actually measure, and describe the trade-offs between different formulations of these properties.

Interpretable Machine Learning

Towards Robust Off-Policy Evaluation via Human Inputs

no code implementations18 Sep 2022 Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

When deployment environments are expected to undergo changes (that is, dataset shifts), it is important for OPE methods to perform robust evaluation of the policies amidst such changes.

Multi-Armed Bandits Off-policy evaluation

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

no code implementations2 Aug 2022 Mark Penrod, Harrison Termotto, Varshini Reddy, Jiayu Yao, Finale Doshi-Velez, Weiwei Pan

For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data.

Decision Making

A Bayesian Approach to Learning Bandit Structure in Markov Decision Processes

no code implementations30 Jul 2022 Kelly W. Zhang, Omer Gottesman, Finale Doshi-Velez

In the reinforcement learning literature, there are many algorithms developed for either Contextual Bandit (CB) or Markov Decision Processes (MDP) environments.

Decision Making reinforcement-learning +1

Policy Optimization with Sparse Global Contrastive Explanations

no code implementations13 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.

reinforcement-learning Reinforcement Learning (RL)

Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines

1 code implementation8 Jun 2022 Anna L. Trella, Kelly W. Zhang, Inbal Nahum-Shani, Vivek Shetty, Finale Doshi-Velez, Susan A. Murphy

Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education.

reinforcement-learning Reinforcement Learning (RL)

Wide Mean-Field Bayesian Neural Networks Ignore the Data

1 code implementation23 Feb 2022 Beau Coker, Wessel P. Bruinsma, David R. Burt, Weiwei Pan, Finale Doshi-Velez

Finally, we show that the optimal approximate posterior need not tend to the prior if the activation function is not odd, showing that our statements cannot be generalized arbitrarily.

Variational Inference

Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making

no code implementations20 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.

counterfactual Decision Making +1

Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation

no code implementations28 Nov 2021 Ramtin Keramati, Omer Gottesman, Leo Anthony Celi, Finale Doshi-Velez, Emma Brunskill

Off-policy policy evaluation methods for sequential decision making can be used to help identify if a proposed decision policy is better than a current baseline policy.

Decision Making

On Learning Prediction-Focused Mixtures

no code implementations25 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.

Time Series Time Series Analysis

Learning Predictive and Interpretable Timeseries Summaries from ICU Data

no code implementations22 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.

Time Series Time Series Analysis

Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning

no code implementations16 Sep 2021 Sarah Rathnam, Susan A. Murphy, Finale Doshi-Velez

In batch reinforcement learning, there can be poorly explored state-action pairs resulting in poorly learned, inaccurate models and poorly performing associated policies.

reinforcement-learning Reinforcement Learning (RL)

State Relevance for Off-Policy Evaluation

1 code implementation13 Sep 2021 Simon P. Shen, Yecheng Jason Ma, Omer Gottesman, Finale Doshi-Velez

Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions.

Off-policy evaluation

Online structural kernel selection for mobile health

no code implementations21 Jul 2021 Eura Shin, Pedja Klasnja, Susan Murphy, Finale Doshi-Velez

Motivated by the need for efficient and personalized learning in mobile health, we investigate the problem of online kernel selection for Gaussian Process regression in the multi-task setting.

regression

Promises and Pitfalls of Black-Box Concept Learning Models

1 code implementation24 Jun 2021 Anita Mahinpei, Justin Clark, Isaac Lage, Finale Doshi-Velez, Weiwei Pan

Machine learning models that incorporate concept learning as an intermediate step in their decision making process can match the performance of black-box predictive models while retaining the ability to explain outcomes in human understandable terms.

Decision Making

Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data

no code implementations13 Jun 2021 Beau Coker, Weiwei Pan, Finale Doshi-Velez

Variational inference enables approximate posterior inference of the highly over-parameterized neural networks that are popular in modern machine learning.

BIG-bench Machine Learning Variational Inference

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning

no code implementations NeurIPS 2021 Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, Milind Tambe

In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.

Reinforcement Learning (RL)

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning

no code implementations NeurIPS 2021 Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, Milind Tambe

In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.

Decision Making Reinforcement Learning (RL)

Learning Under Adversarial and Interventional Shifts

no code implementations29 Mar 2021 Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

Most of the existing work focuses on optimizing for either adversarial shifts or interventional shifts.

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement

1 code implementation9 Feb 2021 Andrew Slavin Ross, Finale Doshi-Velez

In representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs.

Disentanglement

Evaluating the Interpretability of Generative Models by Interactive Reconstruction

1 code implementation2 Feb 2021 Andrew Slavin Ross, Nina Chen, Elisa Zhao Hang, Elena L. Glassman, Finale Doshi-Velez

On synthetic datasets, we find performance on this task much more reliably differentiates entangled and disentangled models than baseline approaches.

Disentanglement

Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible

no code implementations13 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.

Decision Making Management

Artificial Intelligence & Cooperation

no code implementations10 Dec 2020 Elisa Bertino, Finale Doshi-Velez, Maria Gini, Daniel Lopresti, David Parkes

There is a vital need for research in "AI and Cooperation" that seeks to understand the ways in which systems of AIs and systems of AIs with people can engender cooperative behavior.

Decision Making

Incorporating Interpretable Output Constraints in Bayesian Neural Networks

1 code implementation NeurIPS 2020 Wanqian Yang, Lars Lorch, Moritz A. Graule, Himabindu Lakkaraju, Finale Doshi-Velez

Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness.

Fairness Uncertainty Quantification

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks

no code implementations14 Jul 2020 Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks.

Adversarial Robustness

BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty

no code implementations12 Jul 2020 Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift.

Bayesian Inference

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs

1 code implementation NeurIPS 2020 Jianzhun Du, Joseph Futoma, Finale Doshi-Velez

We present two elegant solutions for modeling continuous-time dynamics, in a novel model-based reinforcement learning (RL) framework for semi-Markov decision processes (SMDPs), using neural ordinary differential equations (ODEs).

Model-based Reinforcement Learning reinforcement-learning +1

Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks

no code implementations21 Jun 2020 Sujay Thakur, Cooper Lorsung, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainties by learning features from the data and then performing Bayesian linear regression over these features.

regression

PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes

no code implementations11 Jun 2020 Yash Nair, Finale Doshi-Velez

First, we derive sample complexity bounds for DPL, and then show that model-based learning from expert actions can, even with a finite model class, be impossible.

Imitation Learning

Power Constrained Bandits

1 code implementation13 Apr 2020 Jiayu Yao, Emma Brunskill, Weiwei Pan, Susan Murphy, Finale Doshi-Velez

However, when bandits are deployed in the context of a scientific study -- e. g. a clinical trial to test if a mobile health intervention is effective -- the aim is not only to personalize for an individual, but also to determine, with sufficient statistical power, whether or not the system's intervention is effective.

Decision Making Multi-Armed Bandits

Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders

no code implementations pproximateinference AABI Symposium 2019 Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Recent work shows that traditional training methods tend to yield solutions that violate modeling desiderata: (1) the learned generative model captures the observed data distribution but does so while ignoring the latent codes, resulting in codes that do not represent the data (e. g. van den Oord et al. (2017); Kim et al. (2018)); (2) the aggregate of the learned latent codes does not match the prior p(z).

Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions

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.

Off-policy evaluation reinforcement-learning

Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks

no code implementations12 Dec 2019 Beau Coker, Melanie F. Pradier, Finale Doshi-Velez

While Bayesian neural networks have many appealing characteristics, current priors do not easily allow users to specify basic properties such as expected lengthscale or amplitude variance.

regression

Prediction Focused Topic Models for Electronic Health Records

no code implementations15 Nov 2019 Jason Ren, Russell Kunes, Finale Doshi-Velez

Supervised topic models present an attractive option for incorporating EHR data as features into a prediction problem: given a patient's record, we estimate a set of latent factors that are predictive of the response variable.

Topic Models

Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables

no code implementations1 Nov 2019 Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

Bayesian Neural Networks with Latent Variables (BNN+LVs) capture predictive uncertainty by explicitly modeling model uncertainty (via priors on network weights) and environmental stochasticity (via a latent input noise variable).

Challenges in Computing and Optimizing Upper Bounds of Marginal Likelihood based on Chi-Square Divergences

no code implementations pproximateinference AABI Symposium 2019 Melanie F. Pradier, Michael C. Hughes, Finale Doshi-Velez

Variational inference based on chi-square divergence minimization (CHIVI) provides a way to approximate a model's posterior while obtaining an upper bound on the marginal likelihood.

Variational Inference

Prediction Focused Topic Models via Feature Selection

1 code implementation12 Oct 2019 Jason Ren, Russell Kunes, Finale Doshi-Velez

Supervised topic models are often sought to balance prediction quality and interpretability.

feature selection Topic Models

Optimizing for Interpretability in Deep Neural Networks with Tree Regularization

no code implementations14 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.

Unsupervised Learning of PCFGs with Normalizing Flow

no code implementations ACL 2019 Lifeng Jin, Finale Doshi-Velez, Timothy Miller, Lane Schwartz, William Schuler

This paper describes a neural PCFG inducer which employs context embeddings (Peters et al., 2018) in a normalizing flow model (Dinh et al., 2015) to extend PCFG induction to use semantic and morphological information.

Language Acquisition

Diversity-Inducing Policy Gradient: Using Maximum Mean Discrepancy to Find a Set of Diverse Policies

no code implementations31 May 2019 Muhammad A. Masood, Finale Doshi-Velez

Standard reinforcement learning methods aim to master one way of solving a task whereas there may exist multiple near-optimal policies.

Policy Gradient Methods

Defining Admissible Rewards for High Confidence Policy Evaluation

no code implementations30 May 2019 Niranjani Prasad, Barbara E. Engelhardt, Finale Doshi-Velez

A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy evaluation.

Off-policy evaluation Vocal Bursts Intensity Prediction

Exploring Computational User Models for Agent Policy Summarization

1 code implementation30 May 2019 Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir

We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance.

Imitation Learning

A general method for regularizing tensor decomposition methods via pseudo-data

no code implementations24 May 2019 Omer Gottesman, Weiwei Pan, Finale Doshi-Velez

Tensor decomposition methods allow us to learn the parameters of latent variable models through decomposition of low-order moments of data.

Tensor Decomposition Transfer Learning

Output-Constrained Bayesian Neural Networks

1 code implementation15 May 2019 Wanqian Yang, Lars Lorch, Moritz A. Graule, Srivatsan Srinivasan, Anirudh Suresh, Jiayu Yao, Melanie F. Pradier, Finale Doshi-Velez

Bayesian neural network (BNN) priors are defined in parameter space, making it hard to encode prior knowledge expressed in function space.

Truly Batch Apprenticeship Learning with Deep Successor Features

no code implementations24 Mar 2019 Dong-hun Lee, Srivatsan Srinivasan, Finale Doshi-Velez

We introduce a novel apprenticeship learning algorithm to learn an expert's underlying reward structure in off-policy model-free \emph{batch} settings.

Management

An Evaluation of the Human-Interpretability of Explanation

no code implementations31 Jan 2019 Isaac Lage, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Sam Gershman, Finale Doshi-Velez

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions.

BIG-bench Machine Learning

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

no code implementations16 Nov 2018 Melanie F. Pradier, Weiwei Pan, Jiayu Yao, Soumya Ghosh, Finale Doshi-Velez

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial.

Variational Inference

Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction

1 code implementation EMNLP 2018 Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz

There have been several recent attempts to improve the accuracy of grammar induction systems by bounding the recursive complexity of the induction model (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016; Jin et al., 2018).

Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters

no code implementations3 Jul 2018 Aniruddh Raghu, Omer Gottesman, Yao Liu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown.

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors

2 code implementations ICML 2018 Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties.

Model Selection Open-Ended Question Answering +2

A particle-based variational approach to Bayesian Non-negative Matrix Factorization

no code implementations16 Mar 2018 M. Arjumand Masood, Finale Doshi-Velez

Bayesian Non-negative Matrix Factorization (NMF) is a promising approach for understanding uncertainty and structure in matrix data.

Unsupervised Grammar Induction with Depth-bounded PCFG

1 code implementation TACL 2018 Lifeng Jin, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz

There has been recent interest in applying cognitively or empirically motivated bounds on recursion depth to limit the search space of grammar induction models (Ponvert et al., 2011; Noji and Johnson, 2016; Shain et al., 2016).

How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation

no code implementations2 Feb 2018 Menaka Narayanan, Emily Chen, Jeffrey He, Been Kim, Sam Gershman, Finale Doshi-Velez

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions.

BIG-bench Machine Learning

Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes

1 code implementation NeurIPS 2017 Taylor W. Killian, Samuel Daulton, George Konidaris, Finale Doshi-Velez

We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings.

Transfer Learning

Prediction-Constrained Topic Models for Antidepressant Recommendation

no code implementations1 Dec 2017 Michael C. Hughes, Gabriel Hope, Leah Weiner, Thomas H. McCoy, Roy H. Perlis, Erik B. Sudderth, Finale Doshi-Velez

Supervisory signals can help topic models discover low-dimensional data representations that are more interpretable for clinical tasks.

Topic Models

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

1 code implementation26 Nov 2017 Andrew Slavin Ross, Finale Doshi-Velez

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions themselves can often be fooled by small adversarial perturbations.

Adversarial Robustness

Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning

1 code implementation ICML 2018 Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft

Bayesian neural networks with latent variables are scalable and flexible probabilistic models: They account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns in the data.

Active Learning Decision Making +2

Weighted Tensor Decomposition for Learning Latent Variables with Partial Data

no code implementations18 Oct 2017 Omer Gottesman, Weiwei Pan, Finale Doshi-Velez

Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data.

Tensor Decomposition

Roll-back Hamiltonian Monte Carlo

no code implementations8 Sep 2017 Kexin Yi, Finale Doshi-Velez

We propose a new framework for Hamiltonian Monte Carlo (HMC) on truncated probability distributions with smooth underlying density functions.

Bayesian Inference Computational Efficiency

Prediction-Constrained Training for Semi-Supervised Mixture and Topic Models

no code implementations23 Jul 2017 Michael C. Hughes, Leah Weiner, Gabriel Hope, Thomas H. McCoy Jr., Roy H. Perlis, Erik B. Sudderth, Finale Doshi-Velez

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful.

Sentiment Analysis Topic Models

Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

no code implementations26 Jun 2017 Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft

Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data.

Active Learning reinforcement-learning +2

Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processes

1 code implementation20 Jun 2017 Taylor Killian, Samuel Daulton, George Konidaris, Finale Doshi-Velez

We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings.

Transfer Learning

Model Selection in Bayesian Neural Networks via Horseshoe Priors

1 code implementation29 May 2017 Soumya Ghosh, Finale Doshi-Velez

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties.

Model Selection Open-Ended Question Answering

Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations

1 code implementation10 Mar 2017 Andrew Slavin Ross, Michael C. Hughes, Finale Doshi-Velez

Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test.

Towards A Rigorous Science of Interpretable Machine Learning

no code implementations28 Feb 2017 Finale Doshi-Velez, Been Kim

As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs.

BIG-bench Machine Learning Interpretable Machine Learning +1

Prior matters: simple and general methods for evaluating and improving topic quality in topic modeling

no code implementations12 Jan 2017 Angela Fan, Finale Doshi-Velez, Luke Miratrix

In this work, we first show how the standard topic quality measures of coherence and pointwise mutual information act counter-intuitively in the presence of common but irrelevant words, making it difficult to even quantitatively identify situations in which topics may be dominated by stopwords.

Supervised topic models for clinical interpretability

no code implementations6 Dec 2016 Michael C. Hughes, Huseyin Melih Elibol, Thomas McCoy, Roy Perlis, Finale Doshi-Velez

Supervised topic models can help clinical researchers find interpretable cooccurence patterns in count data that are relevant for diagnostics.

Topic Models

Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes

no code implementations1 Dec 2016 Taylor Killian, George Konidaris, Finale Doshi-Velez

Due to physiological variation, patients diagnosed with the same condition may exhibit divergent, but related, responses to the same treatments.

Transfer Learning

Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input

no code implementations COLING 2016 Cory Shain, William Bryce, Lifeng Jin, Victoria Krakovna, Finale Doshi-Velez, Timothy Miller, William Schuler, Lane Schwartz

This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM).

Language Acquisition Sentence

Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models

no code implementations18 Nov 2016 Viktoriya Krakovna, Finale Doshi-Velez

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions.

speech-recognition Speech Recognition +3

Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models

no code implementations16 Jun 2016 Viktoriya Krakovna, Finale Doshi-Velez

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions.

speech-recognition Speech Recognition +1

Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

2 code implementations23 May 2016 Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning.

Model-based Reinforcement Learning reinforcement-learning +2

Spectral M-estimation with Applications to Hidden Markov Models

no code implementations29 Mar 2016 Dustin Tran, Minjae Kim, Finale Doshi-Velez

Method of moment estimators exhibit appealing statistical properties, such as asymptotic unbiasedness, for nonconvex problems.

Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems

no code implementations28 Apr 2015 Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille

In both cases, there are prior parameters that the user can set to encourage the model to have a desired size and shape, to conform with a domain-specific definition of interpretability.

Attribute General Classification +1

Graph-Sparse LDA: A Topic Model with Structured Sparsity

no code implementations16 Oct 2014 Finale Doshi-Velez, Byron Wallace, Ryan Adams

In our model, topics are summarized by a few latent concept-words from the underlying graph that explain the observed words.

The Infinite Partially Observable Markov Decision Process

no code implementations NeurIPS 2009 Finale Doshi-Velez

The Partially Observable Markov Decision Process (POMDP) framework has proven useful in planning domains that require balancing actions that increase an agents knowledge and actions that increase an agents reward.

Cannot find the paper you are looking for? You can Submit a new open access paper.