11 citations · 27 across the 18 of their papers we have counts for
22 papers
Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac
R. R. Chichili, J. A. Sulskis, R. Sharankova +2
The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally corrected through labor-intensive manual RF adjustments. This proje…
Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
Zhu Wang, Sourav Medya, Sathya N. Ravi
Often, deep network models are purely inductive during training and while performing inference on unseen data. Thus, when such models are used for predictions, it is well known tha…
Using Intermediate Forward Iterates for Intermediate Generator Optimization
Harsh Mishra, Jurijs Nazarovs, Manmohan Dogra +1
Score-based models have recently been introduced as a richer framework to model distributions in high dimensions and are generally more suitable for generative tasks. In score-base…
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
Hamidreza Almasi, Harsh Mishra, Balajee Vamanan +1
Modern ML applications increasingly rely on complex deep learning models and large datasets. There has been an exponential growth in the amount of computation needed to train the l…
Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction Inaccuracies
Priyesh Shukla, Sureshkumar S., Alex C. Stutts +3
We present a novel monocular localization framework by jointly training deep learning-based depth prediction and Bayesian filtering-based pose reasoning. The proposed cross-modal f…
Deep Unlearning via Randomized Conditionally Independent Hessians
Ronak Mehta, Sourav Pal, Vikas Singh +1
Recent legislation has led to interest in machine unlearning, i.e., removing specific training samples from a predictive model as if they never existed in the training dataset. Unl…
Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Vishnu Suresh Lokhande, Rudrasis Chakraborty, Sathya N. Ravi +1
Pooling multiple neuroimaging datasets across institutions often enables improvements in statistical power when evaluating associations (e.g., between risk factors and disease outc…
Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data
Jurijs Nazarovs, Rudrasis Chakraborty, Songwong Tasneeyapant +2
Panel data involving longitudinal measurements of the same set of participants taken over multiple time points is common in studies to understand childhood development and disease…
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi +3
Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of…
Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators
Zihang Meng, Vikas Singh, Sathya N. Ravi
We study how stochastic differential equation (SDE) based ideas can inspire new modifications to existing algorithms for a set of problems in computer vision. Loosely speaking, our…
Learning Invariant Representations using Inverse Contrastive Loss
Aditya Kumar Akash, Vishnu Suresh Lokhande, Sathya N. Ravi +1
Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach corresponds to the so-called information bottleneck principle i…
Physarum Powered Differentiable Linear Programming Layers and Applications
Zihang Meng, Sathya N. Ravi, Vikas Singh
Consider a learning algorithm, which involves an internal call to an optimization routine such as a generalized eigenvalue problem, a cone programming problem or even sorting. Inte…
FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret
Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi +1
Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent t…
Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization offers Significant Performance and Efficiency Gains
Sathya N. Ravi, Abhay Venkatesh, Glenn Moo Fung +1
Data dependent regularization is known to benefit a wide variety of problems in machine learning. Often, these regularizers cannot be easily decomposed into a sum over a finite num…
Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations
Vishnu Suresh Lokhande, Songwong Tasneeyapant, Abhay Venkatesh +2
Rectified Linear Units (ReLUs) are among the most widely used activation function in a broad variety of tasks in vision. Recent theoretical results suggest that despite their excel…
Robust Blind Deconvolution via Mirror Descent
Sathya N. Ravi, Ronak Mehta, Vikas Singh
We revisit the Blind Deconvolution problem with a focus on understanding its robustness and convergence properties. Provable robustness to noise and other perturbations is receivin…
Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
Sathya N. Ravi, Tuan Dinh, Vishnu Lokhande +1
A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages ran…
A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees
Sathya N. Ravi, Maxwell D. Collins, Vikas Singh
We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the sche…
On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation
Vamsi K Ithapu, Sathya N Ravi, Vikas Singh
We study mechanisms to characterize how the asymptotic convergence of backpropagation in deep architectures, in general, is related to the network structure, and how it may be infl…
On the interplay of network structure and gradient convergence in deep learning
Vamsi K Ithapu, Sathya N Ravi, Vikas Singh
The regularization and output consistency behavior of dropout and layer-wise pretraining for learning deep networks have been fairly well studied. However, our understanding of how…
Convergence rates for pretraining and dropout: Guiding learning parameters using network structure
Vamsi K. Ithapu, Sathya Ravi, Vikas Singh
Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit converg…
Convergence of gradient based pre-training in Denoising autoencoders
Vamsi K Ithapu, Sathya Ravi, Vikas Singh
The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network. Various papers have reported extensiv…