Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Singh, Apoorv Vikram"'
We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. We sharpen prior work, proving that accurate recovery in the Wasserstein distance is possible with more noise th
Externí odkaz:
http://arxiv.org/abs/2408.12385
We consider the problem of estimating the spectral density of the normalized adjacency matrix of an $n$-node undirected graph. We provide a randomized algorithm that, with $O(n\epsilon^{-2})$ queries to a degree and neighbor oracle and in $O(n\epsilo
Externí odkaz:
http://arxiv.org/abs/2406.07521
We study lower bounds for the problem of approximating a one dimensional distribution given (noisy) measurements of its moments. We show that there are distributions on $[-1,1]$ that cannot be approximated to accuracy $\epsilon$ in Wasserstein-1 dist
Externí odkaz:
http://arxiv.org/abs/2307.00474
We study the problem of $k$-way clustering in signed graphs. Considerable attention in recent years has been devoted to analyzing and modeling signed graphs, where the affinity measure between nodes takes either positive or negative values. Recently,
Externí odkaz:
http://arxiv.org/abs/2011.01737
$k$-means clustering is NP-hard in the worst case but previous work has shown efficient algorithms assuming the optimal $k$-means clusters are \emph{stable} under additive or multiplicative perturbation of data. This has two caveats. First, we do not
Externí odkaz:
http://arxiv.org/abs/1804.10827
Publikováno v:
Journal of Machine Learning Research
Journal of Machine Learning Research, 2021, 22 (264), pp.1-79
Journal of Machine Learning Research, Microtome Publishing, 2021, 22 (264), pp.1-79
Journal of Machine Learning Research, 2021, 22 (264), pp.1-79
Journal of Machine Learning Research, Microtome Publishing, 2021, 22 (264), pp.1-79
We study the problem of $k$-way clustering in signed graphs. Considerable attention in recent years has been devoted to analyzing and modeling signed graphs, where the affinity measure between nodes takes either positive or negative values. Recently,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59983e82803b52163303c319213eb669
https://inria.hal.science/hal-03101710/document
https://inria.hal.science/hal-03101710/document