1 code implementation • 1 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.
no code implementations • 4 Jun 2023 • Colin Samplawski, Shiwei Fang, Ziqi Wang, Deepak Ganesan, Mani Srivastava, Benjamin M. Marlin
Visual object tracking has seen significant progress in recent years.
no code implementations • 17 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.
no code implementations • 12 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.
no code implementations • 8 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.
no code implementations • 3 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.
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.
no code implementations • 13 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.
1 code implementation • 25 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.
no code implementations • 30 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.
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.
1 code implementation • 8 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
no code implementations • 16 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.
no code implementations • 24 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.
no code implementations • 7 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.
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.
no code implementations • 4 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.
no code implementations • 14 Feb 2019 • Colin Samplawski, Heesung Kwon, Erik Learned-Miller, Benjamin M. Marlin
Zero-shot learning (ZSL) is one of the most extreme forms of learning from scarce labeled data.
1 code implementation • 3 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.
no code implementations • 7 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.
no code implementations • 30 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.
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.
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.