Search Results for author:
Found 32 papers, 6 papers with code
Directly Optimizing Explanations for Desired Properties
When explaining black-box machine learning models, it's often important for explanations to have certain desirable properties.
Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models
Text-to-image (T2I) models are increasingly used in impactful real-life applications.
Inverse Reinforcement Learning with Multiple Planning Horizons
In this work, we study an inverse reinforcement learning (IRL) problem where the experts are planning under a shared reward function but with different, unknown planning horizons.
A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning
Explanations of an AI's function can assist human decision-makers, but the most useful explanation depends on the decision's context, referred to as the downstream task.
Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders
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.
Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks
Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification.
Signature Activation: A Sparse Signal View for Holistic Saliency
The adoption of machine learning in healthcare calls for model transparency and explainability.
Why do universal adversarial attacks work on large language models?: Geometry might be the answer
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.
SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text
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.
The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning
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.
Modeling Mobile Health Users as Reinforcement Learning Agents
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.
An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
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.
What Makes a Good Explanation?: A Harmonized View of Properties of Explanations
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.
Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data.
Policy Optimization with Sparse Global Contrastive Explanations
We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes.
Wide Mean-Field Bayesian Neural Networks Ignore the Data
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.
Promises and Pitfalls of Black-Box Concept Learning Models
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.
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
Variational inference enables approximate posterior inference of the highly over-parameterized neural networks that are popular in modern machine learning.
Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks.
BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift.
Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks
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.
Power Constrained Bandits
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.
Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
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).
Ensembles of Locally Independent Prediction Models
Ensembles depend on diversity for improved performance.
Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
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).
Quality of Uncertainty Quantification for Bayesian Neural Network Inference
Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network.
A general method for regularizing tensor decomposition methods via pseudo-data
Tensor decomposition methods allow us to learn the parameters of latent variable models through decomposition of low-order moments of data.
Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models
Thanks to the combination of a semi-supervised ELBO and parameters sharing across domains, we are able to simultaneously: (i) align all supervised examples of the same class into the same latent Gaussian Mixture component, independently from their domain; (ii) predict the class of unsupervised examples from different domains and use them to better model the occurring shifts.
Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights
As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial.
Learning Qualitatively Diverse and Interpretable Rules for Classification
There has been growing interest in developing accurate models that can also be explained to humans.
Weighted Tensor Decomposition for Learning Latent Variables with Partial Data
Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data.
An Empirical Comparison of Sampling Quality Metrics: A Case Study for Bayesian Nonnegative Matrix Factorization
and (2) How independent are the samples (as MCMC procedures produce correlated samples)?
