Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Aryeh Kontorovich"'
Publikováno v:
IEEE Transactions on Information Theory. 69:3190-3202
We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. As stated, this goal is infeasible without some prior assumptions on the distribution. We discover that a certain information moment assumption renders the
Publikováno v:
Annals of Mathematics and Artificial Intelligence. 89:1215-1235
We consider the problem of cost sensitive multiclass classification, where we would like to increase the sensitivity of an important class at the expense of a less important one. We adopt an {\em apportioned margin} framework to address this problem,
Autor:
Aryeh Kontorovich, Steve Hanneke
Publikováno v:
Theoretical Computer Science. 796:99-113
We provide a new proof that the expected error rate of consistent support vector machines matches the minimax rate (up to a constant factor) in its dependence on the sample size and margin. The upper bound was originally established by [1] , while th
We study the problem of estimating the density $f(\boldsymbol x)$ of a random vector ${\boldsymbol X}$ in $\mathbb R^d$. For a spanning tree $T$ defined on the vertex set $\{1,\dots ,d\}$, the tree density $f_{T}$ is a product of bivariate conditiona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8ffce61daa54a549b94487b09379db9
http://arxiv.org/abs/2111.11971
http://arxiv.org/abs/2111.11971
Publikováno v:
ITA
We extend a recently proposed 1-nearest-neighbor based multiclass learning algorithm and prove that our modification is universally strongly Bayes-consistent in all metric spaces admitting any such learner, making it an "optimistically universal" Bay
Publikováno v:
AAAI
Scopus-Elsevier
Scopus-Elsevier
We propose a hybrid approach to temporal anomaly detection in access data of users to databases --- or more generally, any kind of subject-object co-occurrence data. We consider a high-dimensional setting that also requires fast computation at test t
Autor:
Lee-Ad Gottlieb, Aryeh Kontorovich
Publikováno v:
Information Processing Letters. 174:106179
We generalize the classical notion of packing a set by balls with identical radii to the case where the radii may be different. The largest number of such balls that fit inside the set without overlapping is called its {\em non-uniform packing number
We tackle some fundamental problems in probability theory on corrupted random processes on the integer line. We analyze when a biased random walk is expected to reach its bottommost point and when intervals of integer points can be detected under a n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b049622a9653bac6f99523b048369172
http://arxiv.org/abs/2003.13561
http://arxiv.org/abs/2003.13561
Autor:
Aryeh Kontorovich, Iosif Pinelis
Publikováno v:
Ann. Statist. 47, no. 5 (2019), 2822-2854
We provide an exact non-asymptotic lower bound on the minimax expected excess risk (EER) in the agnostic probably-ap\-proximately-correct (PAC) machine learning classification model and identify minimax learning algorithms as certain maximally symmet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66a5a3d3069ec3062290c1c9540b6834
https://projecteuclid.org/euclid.aos/1564797865
https://projecteuclid.org/euclid.aos/1564797865
Autor:
Aryeh Kontorovich, Daniel Berend
Publikováno v:
Theoretical Computer Science. 652:102-108
The state complexity of a Deterministic Finite-state automaton (DFA) is the number of states in its minimal equivalent DFA. We study the state complexity of random $n$-state DFAs over a $k$-symbol alphabet, drawn uniformly from the set $[n]^{[n]\time