173 citations · 504 across the 54 of their papers we have counts for
28 papers · 1 filter
Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
Gemma J. Anderson, Jim A. Gaffney, Brian K. Spears +3
Large-scale numerical simulations are used across many scientific disciplines to facilitate experimental development and provide insights into underlying physical processes, but th…
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias
Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are e…
Accurate and Robust Feature Importance Estimation under Distribution Shifts
Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Rushil Anirudh +2
With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often use…
Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
Bindya Venkatesh, Jayaraman J. Thiagarajan
Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and t…
Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
Jayaraman J. Thiagarajan, Bindya Venkatesh, Rushil Anirudh +4
Predictive models that accurately emulate complex scientific processes can achieve exponential speed-ups over numerical simulators or experiments, and at the same time provide surr…
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
Bindya Venkatesh, Jayaraman J. Thiagarajan, Kowshik Thopalli +1
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generaliza…
Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
Bindya Venkatesh, Jayaraman J. Thiagarajan
The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exi…
Learn-By-Calibrating: Using Calibration as a Training Objective
Jayaraman J. Thiagarajan, Bindya Venkatesh, Deepta Rajan
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial…
Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
Jayaraman J. Thiagarajan, Bindya Venkatesh, Prasanna Sattigeri +1
With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent…
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
Kowshik Thopalli, Jayaraman J. Thiagarajan, Rushil Anirudh +1
Unsupervised domain adaptation aims to transfer and adapt knowledge learned from a labeled source domain to an unlabeled target domain. Key components of unsupervised domain adapta…
Designing an Effective Metric Learning Pipeline for Speaker Diarization
Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Huan Song +1
State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identitie…
Understanding Deep Neural Networks through Input Uncertainties
Jayaraman J. Thiagarajan, Irene Kim, Rushil Anirudh +1
Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract n…
Unsupervised Dimension Selection using a Blue Noise Spectrum
Jayaraman J. Thiagarajan, Rushil Anirudh, Rahul Sridhar +1
Unsupervised dimension selection is an important problem that seeks to reduce dimensionality of data, while preserving the most useful characteristics. While dimensionality reducti…
GrAMME: Semi-Supervised Learning using Multi-layered Graph Attention Models
Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Huan Song +1
Modern data analysis pipelines are becoming increasingly complex due to the presence of multi-view information sources. While graphs are effective in modeling complex relationships…
Understanding Behavior of Clinical Models under Domain Shifts
Jayaraman J. Thiagarajan, Deepta Rajan, Prasanna Sattigeri
The hypothesis that computational models can be reliable enough to be adopted in prognosis and patient care is revolutionizing healthcare. Deep learning, in particular, has been a…
A Generative Modeling Approach to Limited Channel ECG Classification
Deepta Rajan, Jayaraman J. Thiagarajan
Processing temporal sequences is central to a variety of applications in health care, and in particular multi-channel Electrocardiogram (ECG) is a highly prevalent diagnostic modal…
Exploring High-Dimensional Structure via Axis-Aligned Decomposition of Linear Projections
Jayaraman J. Thiagarajan, Shusen Liu, Karthikeyan Natesan Ramamurthy +1
Two-dimensional embeddings remain the dominant approach to visualize high dimensional data. The choice of embeddings ranges from highly non-linear ones, which can capture complex r…
A Spectral Approach for the Design of Experiments: Design, Analysis and Algorithms
Bhavya Kailkhura, Jayaraman J. Thiagarajan, Charvi Rastogi +2
This paper proposes a new approach to construct high quality space-filling sample designs. First, we propose a novel technique to quantify the space-filling property and optimally…
Attend and Diagnose: Clinical Time Series Analysis using Attention Models
Huan Song, Deepta Rajan, Jayaraman J. Thiagarajan +1
With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Rec…
MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis
Rushil Anirudh, Jayaraman J. Thiagarajan, Rahul Sridhar +1
Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are oth…
Learning Robust Representations for Computer Vision
Peng Zheng, Aleksandr Y. Aravkin, Karthikeyan Natesan Ramamurthy +1
Unsupervised learning techniques in computer vision often require learning latent representations, such as low-dimensional linear and non-linear subspaces. Noise and outliers in th…
Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification
Rushil Anirudh, Jayaraman J. Thiagarajan
Using predictive models to identify patterns that can act as biomarkers for different neuropathoglogical conditions is becoming highly prevalent. In this paper, we consider the pro…
A Deep Learning Approach To Multiple Kernel Fusion
Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri +2
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (…
Robust Local Scaling using Conditional Quantiles of Graph Similarities
Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy +1
Spectral analysis of neighborhood graphs is one of the most widely used techniques for exploratory data analysis, with applications ranging from machine learning to social sciences…