Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Varun Jog"'
Autor:
Varun Jog, James Melbourne
Publikováno v:
Entropy, Vol 22, Iss 3, p 320 (2020)
Entropy and information inequalities are vitally important in many areas of mathematics and engineering [...]
Externí odkaz:
https://doaj.org/article/e76821e899f8410eab9b0172737e5026
Publikováno v:
Entropy, Vol 21, Iss 8, p 809 (2019)
We establish lower bounds on the volume and the surface area of a geometric body using the size of its slices along different directions. In the first part of the paper, we derive volume bounds for convex bodies using generalized subadditivity proper
Externí odkaz:
https://doaj.org/article/f82ab13945214fe6b3bc4ad1759e5159
Publikováno v:
ISIT
The entropy power inequality (EPI) and the Brascamp-Lieb inequality (BLI) are fundamental inequalities concerning the differential entropies of linear transformations of random vectors. The EPI provides lower bounds for the differential entropy of li
Publikováno v:
J Digit Imaging
The purpose of this study is to investigate the robustness of a commonly used convolutional neural network for image segmentation with respect to nearly unnoticeable adversarial perturbations, and suggest new methods to make these networks more robus
Autor:
Muni Sreenivas Pydi, Varun Jog
Publikováno v:
IEEE Transactions on Information Theory. 67:6031-6052
Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial classifiers minimize adversarial risk. In this paper, we analyze adversaria
Publikováno v:
Information and Inference: A Journal of the IMA. 11:959-1036
Estimating the mean of a probability distribution using i.i.d. samples is a classical problem in statistics, wherein finite-sample optimal estimators are sought under various distributional assumptions. In this paper, we consider the problem of mean
Publikováno v:
2022 IEEE International Symposium on Information Theory (ISIT).
Autor:
Arighno Das, Sidharth Gurbani, Meghan G. Lubner, Dane Morgan, Mingren Shen, Leo D. Dreyfuss, E. Jason Abel, Varun Jog
Publikováno v:
Abdominal Radiology. 46:4278-4288
The purpose of this study was to evaluate the use of CT radiomics features and machine learning analysis to identify aggressive tumor features, including high nuclear grade (NG) and sarcomatoid (sarc) features, in large renal cell carcinomas (RCCs).
Publikováno v:
IEEE Journal on Selected Areas in Information Theory. 1:131-144
We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information bottleneck by int
Autor:
Varun Jog
The $r$-parallel set of a measurable set $A \subseteq \mathbb R^d$ is the set of all points whose distance from $A$ is at most $r$. In this paper, we show that the surface area of an $r$-parallel set in $\mathbb R^d$ with volume at most $V$ is upper-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb807f37e54041c69777445db242caf2