85 citations · 114 across the 34 of their papers we have counts for
21 papers · 1 filter
Multi-fidelity Reinforcement Learning Control for Complex Dynamical Systems
Luning Sun, Xin-Yang Liu, Siyan Zhao +3
Controlling instabilities in complex dynamical systems is challenging in scientific and engineering applications. Deep reinforcement learning (DRL) has seen promising results for a…
Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization
Hongjun Choi, Jayaraman J. Thiagarajan, Ruben Glatt +1
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We pr…
On the Use of Anchoring for Training Vision Models
Vivek Narayanaswamy, Kowshik Thopalli, Rushil Anirudh +3
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extra…
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Puja Trivedi, Mark Heimann, Rushil Anirudh +2
While graph neural networks (GNNs) are widely used for node and graph representation learning tasks, the reliability of GNN uncertainty estimates under distribution shifts remains…
Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data
Matthew L. Olson, Shusen Liu, Jayaraman J. Thiagarajan +3
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated supe…
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Puja Trivedi, Mark Heimann, Rushil Anirudh +2
Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI). However, while it is well-known in computer…
PAGER: A Framework for Failure Analysis of Deep Regression Models
Jayaraman J. Thiagarajan, Vivek Narayanaswamy, Puja Trivedi +1
Safe deployment of AI models requires proactive detection of failures to prevent costly errors. To this end, we study the important problem of detecting failures in deep regression…
Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
Matthew L. Olson, Shusen Liu, Rushil Anirudh +3
Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for tools to audit tr…
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
Puja Trivedi, Danai Koutra, Jayaraman J. Thiagarajan
Advances in the expressivity of pretrained models have increased interest in the design of adaptation protocols which enable safe and effective transfer learning. Going beyond conv…
On the Efficacy of Generalization Error Prediction Scoring Functions
Puja Trivedi, Danai Koutra, Jayaraman J. Thiagarajan
Generalization error predictors (GEPs) aim to predict model performance on unseen distributions by deriving dataset-level error estimates from sample-level scores. However, GEPs of…
Analyzing Data-Centric Properties for Graph Contrastive Learning
Puja Trivedi, Ekdeep Singh Lubana, Mark Heimann +2
Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semanti…
Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety
Puja Trivedi, Danai Koutra, Jayaraman J. Thiagarajan
While directly fine-tuning (FT) large-scale, pretrained models on task-specific data is well-known to induce strong in-distribution task performance, recent works have demonstrated…
Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification
Rakshith Subramanyam, Mark Heimann, Jayram Thathachar +2
Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples. Given the inherent diversity…
Single Model Uncertainty Estimation via Stochastic Data Centering
Jayaraman J. Thiagarajan, Rushil Anirudh, Vivek Narayanaswamy +1
We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems. In this paper, we present a str…
Out of Distribution Detection via Neural Network Anchoring
Rushil Anirudh, Jayaraman J. Thiagarajan
Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection. Heteroscedasticity here refers to the fa…
Improving Diversity with Adversarially Learned Transformations for Domain Generalization
Tejas Gokhale, Rushil Anirudh, Jayaraman J. Thiagarajan +3
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Many of the recent success…
Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation
Kowshik Thopalli, Jayaraman J Thiagarajan, Rushil Anirudh +1
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an…
Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization
Kowshik Thopalli, Sameeksha Katoch, Pavan Turaga +1
Domain generalization (DG) methods aim to develop models that generalize to settings where the test distribution is different from the training data. In this paper, we focus on the…
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
Ankita Shukla, Rushil Anirudh, Eugene Kur +5
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion. Unlike a typical hypers…
-UQ: Accurate Uncertainty Quantification via Anchor Marginalization
Rushil Anirudh, Jayaraman J. Thiagarajan
We present -UQ -- a novel, general-purpose uncertainty estimator using the concept of anchoring in predictive models. Anchoring works by first transforming the input into a tupl…
Suppressing simulation bias using multi-modal data
Bogdan Kustowski, Jim A. Gaffney, Brian K. Spears +6
Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with s…