paper-with-me

홈 › Papers

Concentration of Multilinear Functions of the Ising Model with Applications to Network Data

2017-10-11 · NeurIPS 2017 12 · Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath

We prove near-tight concentration of measure for polynomial functions of the Ising model under high temperature. For any degree $d$, we show that a degree-$d$ polynomial of a $n$-spin Ising model exhibits exponential tails that scale as $\exp(-r^{2/d})$ at radius $r=\tilde{\Omega}_d(n^{d/2})$. Our concentration radius is optimal up to logarithmic factors for constant $d$, improving known results by polynomial factors in the number of spins. We demonstrate the efficacy of polynomial functions as statistics for testing the strength of interactions in social networks in both synthetic and real world data.

📄 PDF Abstract BibTeX arXiv:1710.04170

Code (1)

hoonose/multilinear-ising 공식 구현

Similar Papers 제목 키워드 기반

Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI

2018-12-04 · Wenwen Li, Jian Lou, Shuo Zhou, Haiping Lu

While functional magnetic resonance imaging (fMRI) is important for healthcare/neuroscience applications, it is challenging to classify or interpret due to its multi-dimensional structure, high dimensionality, and small …

regression

The Limits of Tractable Marginalization

2025-04-17 · Oliver Broadrick, Sanyam Agarwal, Guy Van Den Broeck, Markus Bläser

Marginalization -- summing a function over all assignments to a subset of its inputs -- is a fundamental computational problem with applications from probabilistic inference to formal verification. Despite its computatio…

Multilinear Operator Networks

2024-01-31 · Yixin Cheng, Grigorios G. Chrysos, Markos Georgopoulos, Volkan Cevher

Despite the remarkable capabilities of deep neural networks in image recognition, the dependence on activation functions remains a largely unexplored area and has yet to be eliminated. On the other hand, Polynomial Netwo…

Novel methods for multilinear data completion and de-noising based on tensor-SVD

2014-07-07 · CVPR 2014 6 · Zemin Zhang, Gregory Ely, Shuchin Aeron, Ning Hao 외

In this paper we propose novel methods for completion (from limited samples) and de-noising of multilinear (tensor) data and as an application consider 3-D and 4- D (color) video data completion and de-noising. We exploi…

Planning with Submodular Objective Functions

2020-10-22 · Ruosong Wang, Hanrui Zhang, Devendra Singh Chaplot, Denis Garagić 외

We study planning with submodular objective functions, where instead of maximizing the cumulative reward, the goal is to maximize the objective value induced by a submodular function. Our framework subsumes standard plan…