no code implementations • 1 May 2024 • Yu-Zhen Janice Chen, Jinhang Zuo, Venugopal V. Veeravalli, Don Towsley
This work studies a QCD problem where the change is either a bad change, which we aim to detect, or a confusing change, which is not of our interest.
no code implementations • 2 Apr 2024 • Aditya Deshmukh, Venugopal V. Veeravalli, Gunjan Verma
Our goal is to design a feature compression {scheme} that can adapt to the varying communication constraints, while maximizing the inference performance at the fusion center.
no code implementations • 1 Nov 2022 • Yuchen Liang, Venugopal V. Veeravalli
The problem of quickest change detection in a sequence of independent observations is considered.
no code implementations • 8 Oct 2022 • Nathan Dahlin, Subhonmesh Bose, Venugopal V. Veeravalli
We consider the control of a Markov decision process (MDP) that undergoes an abrupt change in its transition kernel (mode).
no code implementations • 20 Jul 2022 • Adarsh M. Subramaniam, Akshayaa Magesh, Venugopal V. Veeravalli
Compressed Stochastic Gradient Descent (SGD) algorithms have been recently proposed to address the communication bottleneck in distributed and decentralized optimization problems, such as those that arise in federated machine learning.
no code implementations • 20 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.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 7 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.
no code implementations • 4 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.
no code implementations • 25 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.
no code implementations • 16 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.
no code implementations • 14 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.
no code implementations • 12 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.
no code implementations • 21 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.
no code implementations • 24 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.
no code implementations • 21 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 $T$.
no code implementations • 21 Oct 2019 • Akshayaa Magesh, Venugopal V. Veeravalli
Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems.
1 code implementation • 27 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.
no code implementations • 15 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.
no code implementations • 19 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 $\rho$.
no code implementations • 2 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.
no code implementations • 29 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.
no code implementations • 21 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.
no code implementations • 24 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).
1 code implementation • 19 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