1 code implementation • 17 Sep 2023 • Divya J. Bajpai, Vivek K. Trivedi, Sohan L. Yadav, Manjesh K. Hanawal
To overcome the issue, various approaches are considered, like offloading part of the computation to the cloud for final inference (split computing) or performing the inference at an intermediary layer without passing through all layers (early exits).
Ranked #1 on Paraphrase Identification on IMDb
no code implementations • 15 Aug 2023 • Purushottam Parthasarathy, Avinash Bhardwaj, Manjesh K. Hanawal
We revisit the online portfolio allocation problem and propose universal portfolios that use factor weighing to produce portfolios that out-perform uniform dirichlet allocation schemes.
no code implementations • 26 Dec 2022 • Debamita Ghosh, Haseen Rahman, Manjesh K. Hanawal, Nikola Zlatanov
In this paper, we develop an algorithm that exploits the unimodal structure of the received signal strengths of the beams to identify the best beam in a finite time using pure exploration strategies.
no code implementations • 12 Dec 2022 • Debamita Ghosh, Manjesh K. Hanawal, Nikola Zlatanov
Holographic metasurface transceivers (HMT) is an emerging technology for enhancing the coverage and rate of wireless communication systems.
1 code implementation • 20 Sep 2022 • Hari Narayan N U, Manjesh K. Hanawal, Avinash Bhardwaj
Hence one is faced with the problem of selecting the optimal exit in an unsupervised setting.
no code implementations • 16 Feb 2022 • Manjesh K. Hanawal, Sumit J. Darak
In this work, we treat any such measurable quality that has a non-zero correlation with the rate achieved as side-information and study how it can be exploited to quickly learn the channel that offers higher throughput (reward).
no code implementations • 12 Jul 2021 • Rahul Vaze, Manjesh K. Hanawal
CTMAB is fundamentally different than the usual multi-arm bandit problem (MAB), e. g., even the single-arm case is non-trivial in CTMAB, since the optimal sampling frequency depends on the mean of the arm, which needs to be estimated.
no code implementations • 25 Jun 2021 • Sayan Chatterjee, Manjesh K. Hanawal
Critical role of Internet of Things (IoT) in various domains like smart city, healthcare, supply chain and transportation has made them the target of malicious attacks.
no code implementations • NeurIPS 2021 • 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.
no code implementations • 12 Apr 2021 • Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran
The loss depends on two hidden parameters, one specific to the arm but independent of the resource allocation, and the other depends on the allocated resource.
no code implementations • 12 Jan 2021 • Vinod S. Khandkar, Manjesh K. Hanawal
As the widespread adoption of HTTPS protocol has made it difficult to classify the traffic looking into the content field, one of the fields the middle-boxes look for is Server Name Indicator (SNI), which goes in plain text.
Cryptography and Security Networking and Internet Architecture
no code implementations • 30 Dec 2020 • Debamita Ghosh, Manjesh K. Hanawal, Nikola Zlatanov
We study wireless power transmission by an energy source to multiple energy harvesting nodes with the aim to maximize the energy efficiency.
no code implementations • NeurIPS 2020 • Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári, Venkatesh Saligrama
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 from the observed feedback.
no code implementations • 16 Sep 2020 • Arun Verma, Manjesh K. Hanawal, Nandyala Hemachandra
The total loss is the sum of the cost incurred for selecting the arm and the stochastic loss associated with the selected arm.
no code implementations • 17 Jun 2020 • Arun Verma, Manjesh K. Hanawal
We model this problem setting as a bandit setting where feedback obtained in each round depends on the resource allocated to the agents.
no code implementations • 13 Mar 2020 • Debamita Ghosh, Arun Verma, Manjesh K. Hanawal
It is thus important to learn the least amount of energy harvested by nodes so that the source can transmit on a frequency band that maximizes this amount.
no code implementations • 6 Mar 2020 • Sumit J. Darak, Manjesh K. Hanawal
In this paper, we discuss state-of-the-art multi-armed multi-player bandit based distributed learning algorithms that allow users to adapt to the environment and coordinate with other players/users.
no code implementations • 25 Dec 2019 • 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 invasive tests.
1 code implementation • NeurIPS 2019 • Arun Verma, Manjesh K. Hanawal, Arun Rajkumar, Raman Sankaran
We study this novel setting by establishing its `equivalence' to Multiple-Play Multi-Armed Bandits(MP-MAB) and Combinatorial Semi-Bandits.
no code implementations • 15 Jan 2019 • Arun Verma, Manjesh K. Hanawal, Csaba Szepesvári, Venkatesh Saligrama
We set up the USS problem as a stochastic partial monitoring problem and develop an algorithm with sub-linear regret under the WD property.
1 code implementation • 12 Jan 2019 • Harshvardhan Tibrewal, Sravan Patchala, Manjesh K. Hanawal, Sumit J. Darak
However, such transmissions and sensing for information exchange do not add to network throughput.
no code implementations • 24 Dec 2018 • Sumit J. Darak, Manjesh K. Hanawal
Next generation networks are expected to be ultradense and aim to explore spectrum sharing paradigm that allows users to communicate in licensed, shared as well as unlicensed spectrum.
no code implementations • 17 Sep 2018 • Manjesh K. Hanawal, Sumit J. Darak
We provide algorithms based on a novel `trekking approach' that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability.
no code implementations • 21 Jan 2017 • Manjesh K. Hanawal, Hao liu, Henghui Zhu, Ioannis Ch. Paschalidis
We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs.
no code implementations • 26 Sep 2015 • Manjesh K. Hanawal, Amir Leshem, Venkatesh Saligrama
We then provide a nearly optimal algorithm and show that its expected regret scales as $O(N\log^{1+\epsilon}(T))$ for an arbitrary small $\epsilon >0$.