Search Results for author: Theja Tulabandhula

Found 45 papers, 11 papers with code

CURATRON: Complete Robust Preference Data for Robust Alignment of Large Language Models

no code implementations5 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), with a focus on the issues of incomplete and corrupted data in preference datasets.

InteraRec: Interactive Recommendations Using Multimodal Large Language Models

no code implementations26 Feb 2024 Saketh Reddy Karra, Theja Tulabandhula

Weblogs, comprised of records detailing user activities on any website, offer valuable insights into user preferences, behavior, and interests.

Collaborative Filtering Navigate

Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning

no code implementations11 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.

Atari Games Distributional Reinforcement Learning +2

InteraSSort: Interactive Assortment Planning Using Large Language Models

no code implementations20 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.

Decision Making Management

Conformalized Multimodal Uncertainty Regression and Reasoning

no code implementations20 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.

Conformal Prediction Optical Flow Estimation +2

STARNet: Sensor Trustworthiness and Anomaly Recognition via Approximated Likelihood Regret for Robust Edge Autonomy

1 code implementation20 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.

Dynamic Tiling: A Model-Agnostic, Adaptive, Scalable, and Inference-Data-Centric Approach for Efficient and Accurate Small Object Detection

no code implementations20 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.

Object object-detection +2

Generative AI for Business Strategy: Using Foundation Models to Create Business Strategy Tools

no code implementations27 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.

Decision Making named-entity-recognition +2

Lightweight, Uncertainty-Aware Conformalized Visual Odometry

no code implementations3 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.

Data Augmentation Decision Making +3

Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction Inaccuracies

no code implementations27 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.

Depth Estimation Depth Prediction +1

Estimating the Personality of White-Box Language Models

no code implementations25 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.

Text Generation

ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators

no code implementations12 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.

Computational Efficiency

Choice-Aware User Engagement Modeling andOptimization on Social Media

1 code implementation1 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.

Clustering Multi-Label Classification

Price Discrimination in the Presence of Customer Loyalty and Differing Firm Costs

no code implementations16 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.

Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays

no code implementations16 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

Off-Policy Optimization of Portfolio Allocation Policies under Constraints

1 code implementation21 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.

Decision Making Portfolio Optimization

KATRec: Knowledge Aware aTtentive Sequential Recommendations

1 code implementation6 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.

Graph Attention Representation Learning +1

A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit

no code implementations28 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.

Decision Making Multi-Armed Bandits

Learning by Repetition: Stochastic Multi-armed Bandits under Priming Effect

no code implementations18 Jun 2020 Priyank Agrawal, Theja Tulabandhula

We study the effect of persistence of engagement on learning in a stochastic multi-armed bandit setting.

Decision Making Multi-Armed Bandits +2

Multi-Purchase Behavior: Modeling, Estimation and Optimization

no code implementations14 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.

Optimizing Revenue while showing Relevant Assortments at Scale

1 code implementation6 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).

Information Retrieval Retrieval

$MC^2RAM$: Markov Chain Monte Carlo Sampling in SRAM for Fast Bayesian Inference

no code implementations28 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.

Bayesian Inference

Incentivising Exploration and Recommendations for Contextual Bandits with Payments

no code implementations22 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.

Multi-Armed Bandits

Interpretable User Models via Decision-rule Gaussian Processes: Preliminary Results on Energy Storage

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.

Bayesian Inference Gaussian Processes +1

Thompson Sampling for a Fatigue-aware Online Recommendation System

1 code implementation23 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.

Thompson Sampling

Bandits with Temporal Stochastic Constraints

no code implementations22 Nov 2018 Priyank Agrawal, Theja Tulabandhula

We study the effect of impairment on stochastic multi-armed bandits and develop new ways to mitigate it.

Multi-Armed Bandits

Block-Structure Based Time-Series Models For Graph Sequences

1 code implementation24 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.

Community Detection Time Series +1

An Online Algorithm for Learning Buyer Behavior under Realistic Pricing Restrictions

no code implementations6 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.

Optimizing Revenue over Data-driven Assortments

1 code implementation18 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

Symmetry Learning for Function Approximation in Reinforcement Learning

no code implementations9 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.

reinforcement-learning Reinforcement Learning (RL)

Efficient Reinforcement Learning via Initial Pure Exploration

no code implementations7 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.

Multi-Armed Bandits reinforcement-learning +1

Provable Inductive Robust PCA via Iterative Hard Thresholding

no code implementations2 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.

Learning to Partition using Score Based Compatibilities

no code implementations22 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.

Faster Reinforcement Learning Using Active Simulators

1 code implementation22 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).

reinforcement-learning Reinforcement Learning (RL) +1

Learning Personalized Optimal Control for Repeatedly Operated Systems

no code implementations18 Sep 2016 Theja Tulabandhula

We consider the problem of online learning of optimal control for repeatedly operated systems in the presence of parametric uncertainty.

Reinforcement Learning algorithms for regret minimization in structured Markov Decision Processes

no code implementations17 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.

reinforcement-learning Reinforcement Learning (RL)

Robust Optimization using Machine Learning for Uncertainty Sets

1 code implementation4 Jul 2014 Theja Tulabandhula, Cynthia Rudin

Our goal is to build robust optimization problems for making decisions based on complex data from the past.

BIG-bench Machine Learning Decision Making +1

Generalization Bounds for Learning with Linear, Polygonal, Quadratic and Conic Side Knowledge

1 code implementation30 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.

Generalization Bounds

On Combining Machine Learning with Decision Making

no code implementations27 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.

BIG-bench Machine Learning Decision Making +1

Cannot find the paper you are looking for? You can Submit a new open access paper.