English
Related papers

Related papers: Learning linear structural equation models in poly…

200 papers

Discovering the underlying dynamics of complex systems from data is an important practical topic. Constrained optimization algorithms are widely utilized and lead to many successes. Yet, such purely data-driven methods may bring about…

Dynamical Systems · Mathematics 2023-05-17 Nan Chen , Yinling Zhang

We consider a specific graph learning task: reconstructing a symmetric matrix that represents an underlying graph using linear measurements. We present a sparsity characterization for distributions of random graphs (that are allowed to…

Information Theory · Computer Science 2023-09-08 Tongxin Li , Lucien Werner , Steven H. Low

In the present paper, we propose the model of {\it structural information learning machines} (SiLeM for short), leading to a mathematical definition of learning by merging the theories of computation and information. Our model shows that…

Machine Learning · Computer Science 2020-01-28 Angsheng Li

Sharpness-aware minimization (SAM) has emerged as a highly effective technique to improve model generalization, but its underlying principles are not fully understood. We investigate m-sharpness, where SAM performance improves monotonically…

Machine Learning · Computer Science 2026-04-03 Haocheng Luo , Mehrtash Harandi , Dinh Phung , Trung Le

Causal discovery in real-world systems, such as biological networks, is often complicated by feedback loops and incomplete data. Standard algorithms, which assume acyclic structures or fully observed data, struggle with these challenges. To…

Machine Learning · Statistics 2026-04-07 Muralikrishnna G. Sethuraman , Razieh Nabi , Faramarz Fekri

This paper studies causal discovery for a directed acyclic graph under a structural equation model with additive heteroscedastic errors. We first establish new identifiability results for location-scale noise models, showing that…

Methodology · Statistics 2026-05-27 Xintao Xia , Li Chen , Yue Hu , Chunlin Li

Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combination of features. Estimation in this context requires learning…

Machine Learning · Statistics 2016-12-01 Nikhil Rao , Ravi Ganti , Laura Balzano , Rebecca Willett , Robert Nowak

In this paper, we provide new complexity results for algorithms that learn discrete-variable Bayesian networks from data. Our results apply whenever the learning algorithm uses a scoring criterion that favors the simplest model able to…

Machine Learning · Computer Science 2012-12-12 David Maxwell Chickering , Christopher Meek , David Heckerman

Markov random fields are used to model high dimensional distributions in a number of applied areas. Much recent interest has been devoted to the reconstruction of the dependency structure from independent samples from the Markov random…

Computational Complexity · Computer Science 2010-03-09 Guy Bresler , Elchanan Mossel , Allan Sly

We consider the problem of structure recovery in a graphical model of a tree where some variables are latent. Specifically, we focus on the Gaussian case, which can be reformulated as a well-studied problem: recovering a semi-labeled tree…

Statistics Theory · Mathematics 2025-08-12 Luc Devroye , Gabor Lugosi , Piotr Zwiernik

We introduce DeepMoD, a Deep learning based Model Discovery algorithm. DeepMoD discovers the partial differential equation underlying a spatio-temporal data set using sparse regression on a library of possible functions and their…

Computational Physics · Physics 2021-02-25 Gert-Jan Both , Subham Choudhury , Pierre Sens , Remy Kusters

We introduce a new class of identifiable DAG models where the conditional distribution of each node given its parents belongs to a family of generalized hypergeometric distributions (GHD). A family of generalized hypergeometric…

Machine Learning · Statistics 2019-10-17 Gunwoong Park , Hyewon Park

We consider the problem of exact recovery of a $k$-sparse binary vector from generalized linear measurements (such as logistic regression). We analyze the linear estimation algorithm (Plan, Vershynin, Yudovina, 2017), and also show…

Machine Learning · Statistics 2025-02-25 Arya Mazumdar , Neha Sangwan

We study the fixed design segmented regression problem: Given noisy samples from a piecewise linear function $f$, we want to recover $f$ up to a desired accuracy in mean-squared error. Previous rigorous approaches for this problem rely on…

Machine Learning · Computer Science 2016-07-15 Jayadev Acharya , Ilias Diakonikolas , Jerry Li , Ludwig Schmidt

In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsistency, or consistency in sparsity pattern recovery,…

Machine Learning · Computer Science 2012-02-28 Ali Jalali , Chris Johnson , Pradeep Ravikumar

Learning directed acyclic graphs (DAGs) is long known a critical challenge at the core of probabilistic and causal modeling. The NoTears approach of (Zheng et al., 2018), through a differentiable function involving the matrix exponential…

Machine Learning · Computer Science 2023-10-11 Shuyu Dong , Michèle Sebag

We develop a technique to design efficiently computable estimators for sparse linear regression in the simultaneous presence of two adversaries: oblivious and adaptive. We design several robust algorithms that outperform the state of the…

Machine Learning · Computer Science 2024-11-01 Chih-Hung Liu , Gleb Novikov

We study the problem of PAC learning $\gamma$-margin halfspaces with Random Classification Noise. We establish an information-computation tradeoff suggesting an inherent gap between the sample complexity of the problem and the sample…

Machine Learning · Computer Science 2023-06-29 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

We study a distributed learning problem in which learning agents are embedded in a directed acyclic graph (DAG). There is a fixed and arbitrary distribution over feature/label pairs, and each agent or vertex in the graph is able to directly…

Machine Learning · Computer Science 2025-10-13 Michael Kearns , Aaron Roth , Emily Ryu

We consider the problem of Bayesian causal discovery for the standard model of linear structural equations with equivariant Gaussian noise. A uniform prior is placed on the space of directed acyclic graphs (DAGs) over a fixed set of…

Statistics Theory · Mathematics 2025-07-23 Valentinian Lungu , Joni Shaska , Ioannis Kontoyiannis , Urbashi Mitra