Zobrazeno 1 - 10
of 2 419
pro vyhledávání: '"P, Draganov"'
High-resolution seismic reflections are essential for imaging and monitoring applications. In seismic land surveys using sources and receivers at the surface, surface waves often dominate, masking the reflections. In this study, we demonstrate the ef
Externí odkaz:
http://arxiv.org/abs/2411.02620
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We show that the gradient of the cosine similarity between two points goes to zero in two under-explored settings: (1) if a point has large magnitude or (2) if the points are on opposite ends of the latent space. Counterintuitively, we prove that opt
Externí odkaz:
http://arxiv.org/abs/2406.16468
Autor:
di Montesano, Sebastiano Cultrera, Draganov, Ondrej, Edelsbrunner, Herbert, Saghafian, Morteza
Exploring the shape of point configurations has been a key driver in the evolution of TDA (short for topological data analysis) since its infancy. This survey illustrates the recent efforts to broaden these ideas to model spatial interactions among m
Externí odkaz:
http://arxiv.org/abs/2406.04102
We study the theoretical and practical runtime limits of k-means and k-median clustering on large datasets. Since effectively all clustering methods are slower than the time it takes to read the dataset, the fastest approach is to quickly compress th
Externí odkaz:
http://arxiv.org/abs/2404.01936
Autor:
Draganov, Ondřej, Skiena, Steven
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12080--12099. ACL
Word embeddings represent language vocabularies as clouds of $d$-dimensional points. We investigate how information is conveyed by the general shape of these clouds, instead of representing the semantic meaning of each token. Specifically, we use the
Externí odkaz:
http://arxiv.org/abs/2404.00500
Autor:
di Montesano, Sebastiano Cultrera, Draganov, Ondřej, Edelsbrunner, Herbert, Saghafian, Morteza
Given a finite set, $A \subseteq \mathbb{R}^2$, and a subset, $B \subseteq A$, the \emph{MST-ratio} is the combined length of the minimum spanning trees of $B$ and $A \setminus B$ divided by the length of the minimum spanning tree of $A$. The questio
Externí odkaz:
http://arxiv.org/abs/2403.10204
Autor:
Draganov, Andrew, Dohn, Simon
It has become standard to use gradient-based dimensionality reduction (DR) methods like tSNE and UMAP when explaining what AI models have learned. This makes sense: these methods are fast, robust, and have an uncanny ability to find semantic patterns
Externí odkaz:
http://arxiv.org/abs/2306.11898
Autor:
Draganov, Andrew, Jørgensen, Jakob Rødsgaard, Nellemann, Katrine Scheel, Mottin, Davide, Assent, Ira, Berry, Tyrus, Aslay, Cigdem
tSNE and UMAP are popular dimensionality reduction algorithms due to their speed and interpretable low-dimensional embeddings. Despite their popularity, however, little work has been done to study their full span of differences. We theoretically and
Externí odkaz:
http://arxiv.org/abs/2305.07320
Autor:
Shirmohammadi, Faezeh, Draganov, Deyan, van IJsseldijk, Johno, Ghose, Ranajit, Thorbecke, Jan, Verschuur, Eric, Wapenaar, Kees
The overburden structures often can distort the responses of the target region in seismic data, especially in land datasets. Ideally, all effects of the overburden and underburden structures should be removed, leaving only the responses of the target
Externí odkaz:
http://arxiv.org/abs/2304.09956