1 code implementation • 19 Sep 2024 • Nastaran Darabi, Dinithi Jayasuriya, Devashri Naik, Theja Tulabandhula, Amit Ranjan Trivedi
To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors.
1 code implementation • 12 Jun 2024 • Sina Tayebati, Theja Tulabandhula, Amit R. Trivedi
For example, our extensive evaluations on Waymo, nuScenes, and KITTI datasets show that the approach achieves over a 5% average precision improvement in detection tasks across datasets and over a 4% accuracy improvement in transferring domains from Waymo and nuScenes to KITTI.
no code implementations • 5 Mar 2024 • Son The Nguyen, Niranjan Uma Naresh, Theja Tulabandhula
This paper addresses the challenges of aligning large language models (LLMs) with human values via preference learning (PL), focusing on incomplete and corrupted data in preference datasets.
no code implementations • 26 Feb 2024 • Saketh Reddy Karra, Theja Tulabandhula
Detailed experiments demonstrate the efficacy of the InteraRec framework in delivering valuable and personalized recommendations tailored to individual user preferences.
1 code implementation • 11 Feb 2024 • Alex Christopher Stutts, Danilo Erricolo, Theja Tulabandhula, Amit Ranjan Trivedi
We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks.
no code implementations • 11 Dec 2023 • Son The Nguyen, Theja Tulabandhula, Mary Beth Watson-Manheim
in a fashion similar to generative AI tools, where they can easily provide immediate feedback as well as adapt the deployed models as desired.
no code implementations • 20 Nov 2023 • Saketh Reddy Karra, Theja Tulabandhula
Assortment planning, integral to multiple commercial offerings, is a key problem studied in e-commerce and retail settings.
no code implementations • 20 Sep 2023 • Son The Nguyen, Theja Tulabandhula, Duy Nguyen
We introduce Dynamic Tiling, a model-agnostic, adaptive, and scalable approach for small object detection, anchored in our inference-data-centric philosophy.
no code implementations • 20 Sep 2023 • Domenico Parente, Nastaran Darabi, Alex C. Stutts, Theja Tulabandhula, Amit Ranjan Trivedi
This paper introduces a lightweight uncertainty estimator capable of predicting multimodal (disjoint) uncertainty bounds by integrating conformal prediction with a deep-learning regressor.
1 code implementation • 20 Sep 2023 • Nastaran Darabi, Sina Tayebati, Sureshkumar S., Sathya Ravi, Theja Tulabandhula, Amit R. Trivedi
In diverse test scenarios involving adverse weather and sensor malfunctions, we show that STARNet enhances prediction accuracy by approximately 10% by filtering out untrustworthy sensor streams.
no code implementations • 18 Sep 2023 • Alex C. Stutts, Danilo Erricolo, Sathya Ravi, Theja Tulabandhula, Amit Ranjan Trivedi
In the expanding landscape of AI-enabled robotics, robust quantification of predictive uncertainties is of great importance.
no code implementations • 27 Aug 2023 • Son The Nguyen, Theja Tulabandhula
Generative models (foundation models) such as LLMs (large language models) are having a large impact on multiple fields.
no code implementations • 3 Mar 2023 • Alex C. Stutts, Danilo Erricolo, Theja Tulabandhula, Amit Ranjan Trivedi
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics, and recent progress in the field has produced highly accurate point predictions in complex environments.
no code implementations • 27 Oct 2022 • Priyesh Shukla, Sureshkumar S., Alex C. Stutts, Sathya Ravi, Theja Tulabandhula, Amit R. Trivedi
We present a novel monocular localization framework by jointly training deep learning-based depth prediction and Bayesian filtering-based pose reasoning.
no code implementations • 5 Jul 2022 • Carlo Amodeo, Igor Fortel, Olusola Ajilore, Liang Zhan, Alex Leow, Theja Tulabandhula
Graph theoretical analyses have become standard tools in modeling functional and anatomical connectivity in the brain.
no code implementations • 25 Apr 2022 • Saketh Reddy Karra, Son The Nguyen, Theja Tulabandhula
Our work seeks to address this gap by exploring the personality traits of several large-scale language models designed for open-ended text generation and the datasets used for training them.
no code implementations • 12 Apr 2021 • Shamma Nasrin, Ahish Shylendra, Yuti Kadakia, Nick Iliev, Wilfred Gomes, Theja Tulabandhula, Amit Ranjan Trivedi
Our proposed ENOS framework allows an optimal layer-wise integration of inference operators and computing modes to achieve the desired balance of energy and accuracy.
1 code implementation • 1 Apr 2021 • Saketh Reddy Karra, Theja Tulabandhula
We address the problem of maximizing user engagement with content (in the form of like, reply, retweet, and retweet with comments)on the Twitter platform.
no code implementations • 16 Feb 2021 • Priyesh Shukla, Ankith Muralidhar, Nick Iliev, Theja Tulabandhula, Sawyer B. Fuller, Amit Ranjan Trivedi
Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3D map representation using a harmonic mean of "Gaussian-like" mixture (HMGM) model.
Indoor Localization Robotics Hardware Architecture Image and Video Processing B.7; I.2.9
no code implementations • 16 Feb 2021 • Theja Tulabandhula, Aris Ouksel, Son Nguyen
We study how loyalty behavior of customers and differing costs to produce undifferentiated products by firms can influence market outcomes.
1 code implementation • 21 Dec 2020 • Nymisha Bandi, Theja Tulabandhula
The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk.
1 code implementation • 6 Dec 2020 • Mehrnaz Amjadi, Seyed Danial Mohseni Taheri, Theja Tulabandhula
Sequential recommendation systems model dynamic preferences of users based on their historical interactions with platforms.
no code implementations • 29 Nov 2020 • Tanvir Ahamed, Bo Zou, Nahid Parvez Farazi, Theja Tulabandhula
This paper investigates the problem of assigning shipping requests to ad hoc couriers in the context of crowdsourced urban delivery.
no code implementations • 28 Nov 2020 • Priyank Agrawal, Theja Tulabandhula, Vashist Avadhanula
In this paper, we propose an optimistic algorithm and show that the regret is bounded by $O(\sqrt{dT} + \kappa)$, significantly improving the performance over existing methods.
no code implementations • 18 Jun 2020 • Priyank Agrawal, Theja Tulabandhula
We study the effect of persistence of engagement on learning in a stochastic multi-armed bandit setting.
no code implementations • 14 Jun 2020 • Theja Tulabandhula, Deeksha Sinha, Saketh Reddy Karra, Prasoon Patidar
We study the problem of modeling purchase of multiple products and utilizing it to display optimized recommendations for online retailers and e-commerce platforms.
1 code implementation • 6 Mar 2020 • Theja Tulabandhula, Deeksha Sinha, Saketh Karra
For an arbitrary collection of assortments, our algorithms can find a solution in time that is sub-linear in the number of assortments, and for the simpler case of cardinality constraints - linear in the number of items (existing methods are quadratic or worse).
no code implementations • 28 Feb 2020 • Priyesh Shukla, Ahish Shylendra, Theja Tulabandhula, Amit Ranjan Trivedi
This work discusses the implementation of Markov Chain Monte Carlo (MCMC) sampling from an arbitrary Gaussian mixture model (GMM) within SRAM.
no code implementations • 22 Jan 2020 • Priyank Agrawal, Theja Tulabandhula
We propose a contextual bandit based model to capture the learning and social welfare goals of a web platform in the presence of myopic users.
no code implementations • 19 Nov 2019 • Shamma Nasrin, Srikanth Ramakrishna, Theja Tulabandhula, Amit Ranjan Trivedi
To reduce the power overheads, we propose a dynamic drop out a part of the support parameters.
no code implementations • pproximateinference AABI Symposium 2019 • Danial Mohseni-Taheri, Selvaprabu Nadarajah, Theja Tulabandhula
Models of user behavior are critical inputs in many prescriptive settings and can be viewed as decision rules that transform state information available to the user into actions.
1 code implementation • 23 Jan 2019 • Yunjuan Wang, Theja Tulabandhula
In this paper we consider an online recommendation setting, where a platform recommends a sequence of items to its users at every time period.
no code implementations • 22 Nov 2018 • Priyank Agrawal, Theja Tulabandhula
We study the effect of impairment on stochastic multi-armed bandits and develop new ways to mitigate it.
1 code implementation • 24 Apr 2018 • Mehrnaz Amjadi, Theja Tulabandhula
Although the computational and statistical trade-off for modeling single graphs, for instance, using block models is relatively well understood, extending such results to sequences of graphs has proven to be difficult.
no code implementations • 6 Mar 2018 • Debjyoti Saharoy, Theja Tulabandhula
We propose a new efficient online algorithm to learn the parameters governing the purchasing behavior of a utility maximizing buyer, who responds to prices, in a repeated interaction setting.
1 code implementation • 18 Aug 2017 • Deeksha Sinha, Theja Tulabandhula
For an arbitrary collection of assortments, our algorithms can find a solution in time that is sub-linear in the number of assortments and for the simpler case of cardinality constraints - linear in the number of items (existing methods are quadratic or worse).
Optimization and Control Data Structures and Algorithms
no code implementations • 9 Jun 2017 • Anuj Mahajan, Theja Tulabandhula
In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks which require large amount of training data.
no code implementations • 7 Jun 2017 • Sudeep Raja Putta, Theja Tulabandhula
Based of the scores she obtains in these practice tests, she would formulate a strategy for maximizing her scores in the actual tests.
no code implementations • 2 Apr 2017 • U. N. Niranjan, Arun Rajkumar, Theja Tulabandhula
The robust PCA problem, wherein, given an input data matrix that is the superposition of a low-rank matrix and a sparse matrix, we aim to separate out the low-rank and sparse components, is a well-studied problem in machine learning.
no code implementations • 22 Mar 2017 • Arun Rajkumar, Koyel Mukherjee, Theja Tulabandhula
For one of the four objectives, we show $NP$ hardness under the score structure and give a $\frac{1}{2}$ approximation algorithm for which no constant approximation was known thus far.
1 code implementation • 22 Mar 2017 • Vikas Jain, Theja Tulabandhula
In this work, we propose several online methods to build a \emph{learning curriculum} from a given set of target-task-specific training tasks in order to speed up reinforcement learning (RL).
no code implementations • 18 Sep 2016 • Theja Tulabandhula
We consider the problem of online learning of optimal control for repeatedly operated systems in the presence of parametric uncertainty.
no code implementations • 17 Aug 2016 • K J Prabuchandran, Tejas Bodas, Theja Tulabandhula
A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon.
1 code implementation • 4 Jul 2014 • Theja Tulabandhula, Cynthia Rudin
Our goal is to build robust optimization problems for making decisions based on complex data from the past.
1 code implementation • 30 May 2014 • Theja Tulabandhula, Cynthia Rudin
In this paper, we consider a supervised learning setting where side knowledge is provided about the labels of unlabeled examples.
no code implementations • 3 Dec 2011 • Theja Tulabandhula, Cynthia Rudin
This work proposes a way to align statistical modeling with decision making.
no code implementations • 27 Apr 2011 • Theja Tulabandhula, Cynthia Rudin
We present a new application and covering number bound for the framework of "Machine Learning with Operational Costs (MLOC)," which is an exploratory form of decision theory.