7 citations · 43 across the 68 of their papers we have counts for
28 papers · 1 filter
Stochastic Multi-Armed Bandits with Limited Control Variates
Arun Verma, Manjesh Kumar Hanawal, Arun Rajkumar
Motivated by wireless networks where interference or channel state estimates provide partial insight into throughput, we study a variant of the classical stochastic multi-armed ban…
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inferenc…
Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Early-Exit Deep Neural Networks enable adaptive inference by allowing prediction at intermediary layers, significantly reducing computational costs and latency. Most of the early e…
Know What You Don't Know: Selective Prediction for Early Exit DNNs
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Inference latency and trustworthiness of Deep Neural Networks (DNNs) are the bottlenecks in deploying them in critical applications like sensitive tasks. Early Exit (EE) DNNs overc…
FREE: Fast and Robust Vision Language Models with Early Exits
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world ap…
BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially de…
A Survey of Early Exit Deep Neural Networks in NLP
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Deep Neural Networks (DNNs) have grown increasingly large in size to achieve state of the art performance across a wide range of tasks. However, their high computational requiremen…
Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering Approach
Divya Jyoti Bajpai, Manjesh Kumar Hanawal
Recent advances in Deep Neural Networks (DNNs) have demonstrated outstanding performance across various domains. However, their large size is a challenge for deployment on resource…
FAIR: Filtering of Automatically Induced Rules
Divya Jyoti Bajpai, Ayush Maheshwari, Manjesh Kumar Hanawal +1
The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains. Weak supervi…
I-SplitEE: Image classification in Split Computing DNNs with Early Exits
Divya Jyoti Bajpai, Aastha Jaiswal, Manjesh Kumar Hanawal
The recent advances in Deep Neural Networks (DNNs) stem from their exceptional performance across various domains. However, their inherent large size hinders deploying these networ…
SplitEE: Early Exit in Deep Neural Networks with Split Computing
Divya J. Bajpai, Vivek K. Trivedi, Sohan L. Yadav +1
Deep Neural Networks (DNNs) have drawn attention because of their outstanding performance on various tasks. However, deploying full-fledged DNNs in resource-constrained devices (ed…
ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels
Fathima Zarin Faizal, Adway Girish, Manjesh Kumar Hanawal +1
We study the problem of best-arm identification in a distributed variant of the multi-armed bandit setting, with a central learner and multiple agents. Each agent is associated wit…
Unsupervised Early Exit in DNNs with Multiple Exits
Hari Narayan N U, Manjesh K. Hanawal, Avinash Bhardwaj
Deep Neural Networks (DNNs) are generally designed as sequentially cascaded differentiable blocks/layers with a prediction module connected only to its last layer. DNNs can be atta…
Continuous Time Bandits With Sampling Costs
Rahul Vaze, Manjesh K. Hanawal
We consider a continuous-time multi-arm bandit problem (CTMAB), where the learner can sample arms any number of times in a given interval and obtain a random reward from each sampl…
Stochastic Multi-Armed Bandits with Control Variates
Arun Verma, Manjesh K. Hanawal
This paper studies a new variant of the stochastic multi-armed bandits problem where auxiliary information about the arm rewards is available in the form of control variates. In ma…
Censored Semi-Bandits for Resource Allocation
Arun Verma, Manjesh K. Hanawal, Arun Rajkumar +1
We consider the problem of sequentially allocating resources in a censored semi-bandits setup, where the learner allocates resources at each step to the arms and observes loss. The…
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári +1
In this paper, we study Contextual Unsupervised Sequential Selection (USS), a new variant of the stochastic contextual bandits problem where the loss of an arm cannot be inferred f…
Thompson Sampling for Unsupervised Sequential Selection
Arun Verma, Manjesh K. Hanawal, Nandyala Hemachandra
Thompson Sampling has generated significant interest due to its better empirical performance than upper confidence bound based algorithms. In this paper, we study Thompson Sampling…
Stochastic Network Utility Maximization with Unknown Utilities: Multi-Armed Bandits Approach
Arun Verma, Manjesh K. Hanawal
In this paper, we study a novel Stochastic Network Utility Maximization (NUM) problem where the utilities of agents are unknown. The utility of each agent depends on the amount of…
Learning and Fairness in Energy Harvesting: A Maximin Multi-Armed Bandits Approach
Debamita Ghosh, Arun Verma, Manjesh K. Hanawal
Recent advances in wireless radio frequency (RF) energy harvesting allows sensor nodes to increase their lifespan by remotely charging their batteries. The amount of energy harvest…
Unsupervised Online Feature Selection for Cost-Sensitive Medical Diagnosis
Arun Verma, Manjesh K. Hanawal, Nandyala Hemachandra
In medical diagnosis, physicians predict the state of a patient by checking measurements (features) obtained from a sequence of tests, e.g., blood test, urine test, followed by inv…
Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback
Arun Verma, Manjesh K. Hanawal, Arun Rajkumar +1
In this paper, we study censored Semi-Bandits, a novel variant of the semi-bandits problem. The learner is assumed to have a fixed amount of resources, which it allocates to the ar…
Online Algorithm for Unsupervised Sensor Selection
Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári +1
In many security and healthcare systems, the detection and diagnosis systems use a sequence of sensors/tests. Each test outputs a prediction of the latent state and carries an inhe…
Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous Networks
Harshvardhan Tibrewal, Sravan Patchala, Manjesh K. Hanawal +1
We consider an ad hoc network where multiple users access the same set of channels. The channel characteristics are unknown and could be different for each user (heterogeneous). No…