Search Results for author: Venugopal V. Veeravalli

Found 19 papers, 2 papers with code

Multiple Testing Framework for Out-of-Distribution Detection

no code implementations20 Jun 2022 Akshayaa Magesh, Venugopal V. Veeravalli, Anirban Roy, Susmit Jha

While a number of tests for OOD detection have been proposed in prior work, a formal framework for studying this problem is lacking.

OOD Detection Out-of-Distribution Detection

Quickest Change Detection in the Presence of Transient Adversarial Attacks

no code implementations7 Jun 2022 Thirupathaiah Vasantam, Don Towsley, Venugopal V. Veeravalli

We study a monitoring system in which the distributions of sensors' observations change from a nominal distribution to an abnormal distribution in response to an adversary's presence.

Change Detection

Quickest Change Detection with Non-Stationary Post-Change Observations

no code implementations4 Oct 2021 Yuchen Liang, Alexander G. Tartakovsky, Venugopal V. Veeravalli

For the case where the post-change distributions have parametric uncertainty, a window-limited (WL) generalized likelihood-ratio (GLR) CuSum procedure is developed and is shown to achieve the universal lower bound asymptotically.

Change Detection

Non-Parametric Quickest Mean Change Detection

no code implementations25 Aug 2021 Yuchen Liang, Venugopal V. Veeravalli

For the case where the pre-change distribution is known, a test is derived that asymptotically minimizes the worst-case detection delay over all possible post-change distributions, as the false alarm rate goes to zero.

Change Detection

Resource Allocation in NOMA-based Self-Organizing Networks using Stochastic Multi-Armed Bandits

no code implementations16 Jan 2021 Marie Josepha Youssef, Venugopal V. Veeravalli, Joumana Farah, Charbel Abdel Nour, Catherine Douillard

In contrast to previous work on channel allocation using the MAB framework, APs are permitted to choose multiple channels for transmission.

Multi-Armed Bandits

Non-Parametric Quickest Detection of a Change in the Mean of an Observation Sequence

no code implementations14 Jan 2021 Yuchen Liang, Venugopal V. Veeravalli

We study the problem of quickest detection of a change in the mean of an observation sequence, under the assumption that both the pre- and post-change distributions have bounded support.

Dynamic Spectrum Access using Stochastic Multi-User Bandits

no code implementations12 Jan 2021 Meghana Bande, Akshayaa Magesh, Venugopal V. Veeravalli

In contrast to prior work, it is assumed that rewards can be non-zero even under collisions, thus allowing for the number of users to be greater than the number of channels.

Robust Mean Estimation in High Dimensions via $\ell_0$ Minimization

no code implementations21 Aug 2020 Jing Liu, Aditya Deshmukh, Venugopal V. Veeravalli

We study the robust mean estimation problem in high dimensions, where $\alpha <0. 5$ fraction of the data points can be arbitrarily corrupted.

Compressive Sensing

Sequential Controlled Sensing for Composite Multihypothesis Testing

no code implementations24 Oct 2019 Aditya Deshmukh, Srikrishna Bhashyam, Venugopal V. Veeravalli

The distribution of observations collected under each control is assumed to follow a single-parameter exponential family distribution.

Two-sample testing

Decentralized Heterogeneous Multi-Player Multi-Armed Bandits with Non-Zero Rewards on Collisions

no code implementations21 Oct 2019 Akshayaa Magesh, Venugopal V. Veeravalli

Within this setup, where the number of players is allowed to be greater than the number of arms, we present a policy that achieves near order-optimal expected regret of order $O(\log^{1 + \delta} T)$ for some $0 < \delta < 1$ over a time-horizon of duration $T$.

Multi-Armed Bandits

Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access

no code implementations21 Oct 2019 Akshayaa Magesh, Venugopal V. Veeravalli

Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems.

Multi-Armed Bandits

Information-Theoretic Understanding of Population Risk Improvement with Model Compression

1 code implementation27 Jan 2019 Yuheng Bu, Weihao Gao, Shaofeng Zou, Venugopal V. Veeravalli

We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression.

Model Compression

Tightening Mutual Information Based Bounds on Generalization Error

no code implementations15 Jan 2019 Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

The bound is derived under more general conditions on the loss function than in existing studies; nevertheless, it provides a tighter characterization of the generalization error.

Model change detection with application to machine learning

no code implementations19 Nov 2018 Yuheng Bu, Jiaxun Lu, Venugopal V. Veeravalli

The goal is to detect whether the change in the model is significant, i. e., whether the difference between the pre-change parameter and the post-change parameter $\|\theta-\theta'\|_2$ is larger than a pre-determined threshold $\rho$.

Change Detection

Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access

no code implementations2 Jul 2018 Meghana Bande, Venugopal V. Veeravalli

The algorithms in both stochastic and adversarial scenarios are extended to the dynamic case where the number of users in the system evolves over time and are shown to lead to sub-linear regret.

Multi-Armed Bandits

Active and Adaptive Sequential learning

no code implementations29 May 2018 Yuheng Bu, Jiaxun Lu, Venugopal V. Veeravalli

Furthermore, an estimator of the change in the learning problems using the active learning samples is constructed, which provides an adaptive sample size selection rule that guarantees the excess risk is bounded for sufficiently large number of time steps.

Active Learning

Linear-Complexity Exponentially-Consistent Tests for Universal Outlying Sequence Detection

no code implementations21 Jan 2017 Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli

A sequence is considered as outlying if the observations therein are generated by a distribution different from those generating the observations in the majority of the sequences.

Adaptive Sequential Optimization with Applications to Machine Learning

no code implementations24 Sep 2015 Craig Wilson, Venugopal V. Veeravalli

A framework is introduced for solving a sequence of slowly changing optimization problems, including those arising in regression and classification applications, using optimization algorithms such as stochastic gradient descent (SGD).

General Classification

Quickest Change Detection

1 code implementation19 Oct 2012 Venugopal V. Veeravalli, Taposh Banerjee

The problem of detecting changes in the statistical properties of a stochastic system and time series arises in various branches of science and engineering.

Statistics Theory Information Theory Information Theory Optimization and Control Probability Applications Statistics Theory

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