48 citations · 57 across the 11 of their papers we have counts for
13 papers
Breakdance Video classification in the age of Generative AI
Sauptik Dhar, Naveen Ramakrishnan, Michelle Munson
Large Vision Language models have seen huge application in several sports use-cases recently. Most of these works have been targeted towards a limited subset of popular sports like…
Large VLM-based Stylized Sports Captioning
Sauptik Dhar, Nicholas Buoncristiani, Joe Anakata +2
The advent of large (visual) language models (LLM / LVLM) have led to a deluge of automated human-like systems in several domains including social media content generation, search…
A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it
Viswanath Ganapathy, Sauptik Dhar, Olimpiya Saha +3
In recent times, advances in artificial intelligence (AI) and IoT have enabled seamless and viable maintenance of appliances in home and building environments. Several studies have…
Universum GANs: Improving GANs through contradictions
Sauptik Dhar, Javad Heydari, Samarth Tripathi +2
Limited availability of labeled-data makes any supervised learning problem challenging. Alternative learning settings like semi-supervised and universum learning alleviate the depe…
DOC3-Deep One Class Classification using Contradictions
Sauptik Dhar, Bernardo Gonzalez Torres
This paper introduces the notion of learning from contradictions (a.k.a Universum learning) for deep one class classification problems. We formalize this notion for the widely adop…
Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
Sauptik Dhar, Unmesh Kurup, Mohak Shah
This research proposes to use the Moreau-Yosida envelope to stabilize the convergence behavior of bi-level Hyperparameter optimization solvers, and introduces the new algorithm cal…
On-Device Machine Learning: An Algorithms and Learning Theory Perspective
Sauptik Dhar, Junyao Guo, Jiayi Liu +3
The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with i…
Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize
Youngsuk Park, Sauptik Dhar, Stephen Boyd +1
Variable metric proximal gradient (VM-PG) is a widely used class of convex optimization method. Lately, there has been a lot of research on the theoretical guarantees of VM-PG with…
Single Class Universum-SVM
Sauptik Dhar, Vladimir Cherkassky
This paper extends the idea of Universum learning [1, 2] to single-class learning problems. We propose Single Class Universum-SVM setting that incorporates a priori knowledge (in t…
Improving Model Training by Periodic Sampling over Weight Distributions
Samarth Tripathi, Jiayi Liu, Unmesh Kurup +2
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentu…
Multiclass Universum SVM
Sauptik Dhar, Vladimir Cherkassky, Mohak Shah
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose an analytic span bound for model sele…
Universum Learning for Multiclass SVM
Sauptik Dhar, Naveen Ramakrishnan, Vladimir Cherkassky +1
We introduce Universum learning for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose a span bound for MU-SVM that can be u…
Universum Learning for SVM Regression
Sauptik Dhar, Vladimir Cherkassky
This paper extends the idea of Universum learning [18, 19] to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowl…