Zobrazeno 1 - 10
of 751
pro vyhledávání: '"Miklós Z"'
Autor:
Rácz, Miklós Z., Zhang, Jifan
We study the problem of learning latent community structure from multiple correlated networks, focusing on edge-correlated stochastic block models with two balanced communities. Recent work of Gaudio, R\'acz, and Sridhar (COLT 2022) determined the pr
Externí odkaz:
http://arxiv.org/abs/2412.02796
Autor:
Chai, Shuwen, Rácz, Miklós Z.
We study learning problems on correlated stochastic block models with two balanced communities. Our main result gives the first efficient algorithm for graph matching in this setting. In the most interesting regime where the average degree is logarit
Externí odkaz:
http://arxiv.org/abs/2412.02661
Autor:
Rácz, Miklós Z., Sridhar, Anirudh
We consider the task of estimating the latent vertex correspondence between two edge-correlated random graphs with generic, inhomogeneous structure. We study the so-called \emph{$k$-core estimator}, which outputs a vertex correspondence that induces
Externí odkaz:
http://arxiv.org/abs/2302.05407
We propose a simple and efficient local algorithm for graph isomorphism which succeeds for a large class of sparse graphs. This algorithm produces a low-depth canonical labeling, which is a labeling of the vertices of the graph that identifies its is
Externí odkaz:
http://arxiv.org/abs/2211.16454
Autor:
Racz, Miklos Z., Rigobon, Daniel E.
This paper studies how a centralized planner can modify the structure of a social or information network to reduce polarization. First, polarization is found to be highly dependent on degree and structural properties of the network -- including the w
Externí odkaz:
http://arxiv.org/abs/2206.08996
Tree-based models are used in many high-stakes application domains such as finance and medicine, where robustness and interpretability are of utmost importance. Yet, methods for improving and certifying their robustness are severely under-explored, i
Externí odkaz:
http://arxiv.org/abs/2205.13909
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting their real-w
Externí odkaz:
http://arxiv.org/abs/2204.00487
We consider the problem of learning latent community structure from multiple correlated networks. We study edge-correlated stochastic block models with two balanced communities, focusing on the regime where the average degree is logarithmic in the nu
Externí odkaz:
http://arxiv.org/abs/2203.15736
Autor:
Liu, Suqi, Racz, Miklos Z.
We study random graphs with latent geometric structure, where the probability of each edge depends on the underlying random positions corresponding to the two endpoints. We focus on the setting where this conditional probability is a general monotone
Externí odkaz:
http://arxiv.org/abs/2110.15886
Correlated Stochastic Block Models: Exact Graph Matching with Applications to Recovering Communities
Autor:
Racz, Miklos Z., Sridhar, Anirudh
We consider the task of learning latent community structure from multiple correlated networks. First, we study the problem of learning the latent vertex correspondence between two edge-correlated stochastic block models, focusing on the regime where
Externí odkaz:
http://arxiv.org/abs/2107.06767