Search Results for author: Benjamin M. Marlin

Found 24 papers, 7 papers with code

REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning

1 code implementation1 Nov 2023 Maxwell A. Xu, Alexander Moreno, Hui Wei, Benjamin M. Marlin, James M. Rehg

The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks.

Contrastive Learning Retrieval +1

Assessing the Impact of Context Inference Error and Partial Observability on RL Methods for Just-In-Time Adaptive Interventions

no code implementations17 May 2023 Karine Karine, Predrag Klasnja, Susan A. Murphy, Benjamin M. Marlin

Just-in-Time Adaptive Interventions (JITAIs) are a class of personalized health interventions developed within the behavioral science community.

BayesLDM: A Domain-Specific Language for Probabilistic Modeling of Longitudinal Data

no code implementations12 Sep 2022 Karine Tung, Steven De La Torre, Mohamed El Mistiri, Rebecca Braga De Braganca, Eric Hekler, Misha Pavel, Daniel Rivera, Pedja Klasnja, Donna Spruijt-Metz, Benjamin M. Marlin

In this paper we present BayesLDM, a system for Bayesian longitudinal data modeling consisting of a high-level modeling language with specific features for modeling complex multivariate time series data coupled with a compiler that can produce optimized probabilistic program code for performing inference in the specified model.

Bayesian Inference Time Series +1

Impact of Parameter Sparsity on Stochastic Gradient MCMC Methods for Bayesian Deep Learning

no code implementations8 Feb 2022 Meet P. Vadera, Adam D. Cobb, Brian Jalaian, Benjamin M. Marlin

In this paper, we investigate the potential of sparse network structures to flexibly trade-off model storage costs and inference run time against predictive performance and uncertainty quantification ability.

Bayesian Inference Uncertainty Quantification

Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systems

no code implementations3 Dec 2021 Meet P. Vadera, Benjamin M. Marlin

Approximate Bayesian deep learning methods hold significant promise for addressing several issues that occur when deploying deep learning components in intelligent systems, including mitigating the occurrence of over-confident errors and providing enhanced robustness to out of distribution examples.

Bayesian Inference

Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series

1 code implementation ICLR 2023 Satya Narayan Shukla, Benjamin M. Marlin

Irregularly sampled time series commonly occur in several domains where they present a significant challenge to standard deep learning models.

Time Series Time Series Analysis

Post-hoc loss-calibration for Bayesian neural networks

no code implementations13 Jun 2021 Meet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin

Bayesian decision theory provides an elegant framework for acting optimally under uncertainty when tractable posterior distributions are available.

Decision Making

Multi-Time Attention Networks for Irregularly Sampled Time Series

1 code implementation25 Jan 2021 Satya Narayan Shukla, Benjamin M. Marlin

Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models.

Time Series Time Series Analysis

A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series

no code implementations30 Nov 2020 Satya Narayan Shukla, Benjamin M. Marlin

Such data represent fundamental challenges to many classical models from machine learning and statistics due to the presence of non-uniform intervals between observations.

Astronomy BIG-bench Machine Learning +2

Learning from Irregularly-Sampled Time Series: A Missing Data Perspective

1 code implementation ICML 2020 Steven Cheng-Xian Li, Benjamin M. Marlin

We model observed irregularly-sampled time series data as a sequence of index-value pairs sampled from a continuous but unobserved function.

Time Series Time Series Analysis

URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks

1 code implementation8 Jul 2020 Meet P. Vadera, Adam D. Cobb, Brian Jalaian, Benjamin M. Marlin

In this paper, we describe initial work on the development ofURSABench(the Uncertainty, Robustness, Scalability, and Accu-racy Benchmark), an open-source suite of bench-marking tools for comprehensive assessment of approximate Bayesian inference methods with a focus on deep learning-based classification tasks

Bayesian Inference Benchmarking

Generalized Bayesian Posterior Expectation Distillation for Deep Neural Networks

no code implementations16 May 2020 Meet P. Vadera, Brian Jalaian, Benjamin M. Marlin

In this paper, we present a general framework for distilling expectations with respect to the Bayesian posterior distribution of a deep neural network classifier, extending prior work on the Bayesian Dark Knowledge framework.

Out-of-Distribution Detection

Integrating Physiological Time Series and Clinical Notes with Deep Learning for Improved ICU Mortality Prediction

no code implementations24 Mar 2020 Satya Narayan Shukla, Benjamin M. Marlin

Intensive Care Unit Electronic Health Records (ICU EHRs) store multimodal data about patients including clinical notes, sparse and irregularly sampled physiological time series, lab results, and more.

ICU Mortality Time Series +1

Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification

no code implementations7 Feb 2020 Meet P. Vadera, Satya Narayan Shukla, Brian Jalaian, Benjamin M. Marlin

In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations.

Adversarial Robustness General Classification

Interpolation-Prediction Networks for Irregularly Sampled Time Series

1 code implementation ICLR 2019 Satya Narayan Shukla, Benjamin M. Marlin

The interpolation network allows for information to be shared across multiple dimensions of a multivariate time series during the interpolation stage, while any standard deep learning model can be used for the prediction network.

Length-of-Stay prediction Mortality Prediction +3

Assessing the Robustness of Bayesian Dark Knowledge to Posterior Uncertainty

no code implementations4 Jun 2019 Meet P. Vadera, Benjamin M. Marlin

Bayesian Dark Knowledge is a method for compressing the posterior predictive distribution of a neural network model into a more compact form.

General Classification

Modeling Irregularly Sampled Clinical Time Series

1 code implementation3 Dec 2018 Satya Narayan Shukla, Benjamin M. Marlin

In this paper, we present a new deep learning architecture for addressing this problem based on the use of a semi-parametric interpolation network followed by the application of a prediction network.

Length-of-Stay prediction Time Series +1

Learning Time Series Detection Models from Temporally Imprecise Labels

no code implementations7 Nov 2016 Roy J. Adams, Benjamin M. Marlin

In this paper, we consider a new low-quality label learning problem: learning time series detection models from temporally imprecise labels.

Multiple Instance Learning Time Series +1

Learning Tree-Structured Detection Cascades for Heterogeneous Networks of Embedded Devices

no code implementations30 Jul 2016 Hamid Dadkhahi, Benjamin M. Marlin

Different nodes have access to different features, as well as access to potentially different computation and energy resources.

Activity Recognition

Variational bounds for mixed-data factor analysis

no code implementations NeurIPS 2010 Mohammad E. Khan, Guillaume Bouchard, Kevin P. Murphy, Benjamin M. Marlin

We show that EM is significantly more robust in the presence of missing data compared to treating the latent factors as parameters, which is the approach used by exponential family PCA and other related matrix-factorization methods.

Accelerating Bayesian Structural Inference for Non-Decomposable Gaussian Graphical Models

no code implementations NeurIPS 2009 Baback Moghaddam, Emtiyaz Khan, Kevin P. Murphy, Benjamin M. Marlin

In this paper we make several contributions towards accelerating approximate Bayesian structural inference for non-decomposable GGMs.

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