English
Related papers

Related papers: Symbolic analytic spread: upper bounds and applica…

200 papers

Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-modal structures. However, theoretical understanding of their…

Machine Learning · Statistics 2026-05-29 Jingda Wu , Changxiao Cai

Will a new smartphone application diffuse deeply in the population or will it sink into oblivion soon? To predict this, we argue that common models of spread of innovations based on cascade dynamics or epidemics may not be fully adequate.…

Social and Information Networks · Computer Science 2021-03-02 Fabio Fagnani , Lorenzo Zino

We study the regularity of symbolic powers of square-free monomial ideals. We prove that if $I = I_\Delta$ is the Stanley-Reisner ideal of a simplicial complex $\Delta$, then $\reg(I^{(n)}) \leqslant \delta(n-1) +b$ for all $n\geqslant 1$,…

Commutative Algebra · Mathematics 2021-08-24 Truong Thi Hien , Tran Nam Trung

Statisticians increasingly face the problem to reconsider the adaptability of classical inference techniques. In particular, divers types of high-dimensional data structures are observed in various research areas; disclosing the boundaries…

Statistics Theory · Mathematics 2017-06-09 Paavo Sattler , Markus Pauly

Diffusion models, a powerful and universal generative AI technology, have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. In these applications, diffusion models provide flexible…

Machine Learning · Computer Science 2024-04-12 Minshuo Chen , Song Mei , Jianqing Fan , Mengdi Wang

In this article we present an algorithm to compute bounds on the marginals of a graphical model. For several small clusters of nodes upper and lower bounds on the marginal values are computed independently of the rest of the network. The…

Artificial Intelligence · Computer Science 2011-06-27 B. Kappen , M. Leisink

Let $m$, $n$, $a_1$, ..., $a_r$, $b_1$, ..., $b_r$ be integers with $1\leq a_1<...<a_r\leq m$ and $1\leq b_1<...<b_r\leq n$. And let $x$ be the universal $m\times n$ matrix with the property that $i$-minors of first $a_i-1$ rows and first…

Commutative Algebra · Mathematics 2007-05-23 Mitsuhiro Miyazaki

Neuro-symbolic AI is an effective method for improving the overall performance of AI models by combining the advantages of neural networks and symbolic learning. However, there are differences between the two in terms of how they process…

Artificial Intelligence · Computer Science 2024-11-08 Xin Zhang , Victor S. Sheng

Ideas by Statistical Mechanics (ISM) is a generic program to model evolution and propagation of ideas/patterns throughout populations subjected to endogenous and exogenous interactions. The program is based on the author's work in…

Computational Engineering, Finance, and Science · Computer Science 2007-05-23 Lester Ingber

Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditionally, symbolic regression methods use hand-designed…

Machine Learning · Computer Science 2021-06-14 Luca Biggio , Tommaso Bendinelli , Alexander Neitz , Aurelien Lucchi , Giambattista Parascandolo

By use of the threshold expansion we develop an algorithm for analytical evaluation, within dimensional regularization, of arbitrary terms in the expansion of the (two-loop) sunset diagram with general masses m_1, m_2 and m_3 near its…

High Energy Physics - Phenomenology · Physics 2010-11-15 A. I. Davydychev , V. A. Smirnov

Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge of the training data is currently lacking. Huge…

Disordered Systems and Neural Networks · Physics 2024-06-27 R. Pacelli , S. Ariosto , M. Pastore , F. Ginelli , M. Gherardi , P. Rotondo

One deals with catalectic codimension two perfect ideals and certain degenerations thereof, with a view towards the nature of their symbolic powers. In the spirit of [10] one considers linearly presented such ideals, only now in the…

Commutative Algebra · Mathematics 2014-05-20 A. Simis , Z. Ramos

In the context of algebraic statistics an experimental design is described by a set of polynomials called the design ideal. This, in turn, is generated by finite sets of polynomials. Two types of generating sets are mostly used in the…

Methodology · Statistics 2008-09-10 Roberto Notari , Eva Riccomagno , Maria-Piera Rogantin

Shearer's inequality bounds the sum of joint entropies of random variables in terms of the total joint entropy. We give another lower bound for the same sum in terms of the individual entropies when the variables are functions of…

Probability · Mathematics 2021-03-23 Endre Csóka , Viktor Harangi , Bálint Virág

Symbolic regression is a powerful system identification technique in industrial scenarios where no prior knowledge on model structure is available. Such scenarios often require specific model properties such as interpretability, robustness,…

Score-based diffusion models have demonstrated outstanding empirical performance in machine learning and artificial intelligence, particularly in generating high-quality new samples from complex probability distributions. Improving the…

Machine Learning · Statistics 2025-05-30 Yuchen Jiao , Gen Li

Associated to any hypergraph is a toric ideal encoding the algebraic relations among its edges. We study these ideals and the combinatorics of their minimal generators, and derive general degree bounds for both uniform and non-uniform…

Commutative Algebra · Mathematics 2012-12-24 Elizabeth Gross , Sonja Petrović

When does a Noetherian commutative ring $R$ have uniform symbolic topologies on primes--read, when does there exist an integer $D>0$ such that the symbolic power $P^{(Dr)} \subseteq P^r$ for all prime ideals $P \subseteq R$ and all $r >0$?…

Commutative Algebra · Mathematics 2018-11-26 Robert M. Walker

Influence maximization (IM) is the problem of finding for a given $s\geq 1$ a set $S$ of $|S|=s$ nodes in a network with maximum influence. With stochastic diffusion models, the influence of a set $S$ of seed nodes is defined as the…

Machine Learning · Computer Science 2019-10-30 Gal Sadeh , Edith Cohen , Haim Kaplan
‹ Prev 1 4 5 6 7 8 10 Next ›