English
Related papers

Related papers: From Sets to Multisets: Provable Variational Infer…

200 papers

The scalability of submodular optimization methods is critical for their usability in practice. In this paper, we study the reducibility of submodular functions, a property that enables us to reduce the solution space of submodular…

Machine Learning · Computer Science 2016-01-05 Jincheng Mei , Hao Zhang , Bao-Liang Lu

We establish analogues in the context of group actions or group representations of some classical problems and results in additive combinatorics of groups. We also study the notion of left invariant submodular function defined on power sets…

Combinatorics · Mathematics 2024-04-17 Vincent Beck , Cédric Lecouvey

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…

Machine Learning · Computer Science 2021-01-19 Sumukh Aithal K , Dhruva Kashyap , Natarajan Subramanyam

This paper considers generalized linear models using rule-based features, also referred to as rule ensembles, for regression and probabilistic classification. Rules facilitate model interpretation while also capturing nonlinear dependences…

Machine Learning · Computer Science 2019-06-06 Dennis Wei , Sanjeeb Dash , Tian Gao , Oktay Günlük

Probabilistic inference is a fundamental task in modern machine learning. Recent advances in tensor network (TN) contraction algorithms have enabled the development of better exact inference methods. However, many common inference tasks in…

Machine Learning · Computer Science 2024-09-10 Martin Roa-Villescas , Xuanzhao Gao , Sander Stuijk , Henk Corporaal , Jin-Guo Liu

Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference. The accuracy of the marginals depends crucially on the quality of the submodular extension. To identify the best…

Machine Learning · Computer Science 2018-01-22 Pankaj Pansari , Chris Russell , M. Pawan Kumar

Probabilistic theory and differential equation are powerful tools for the interpretability and guidance of the design of machine learning models, especially for illuminating the mathematical motivation of learning latent variable from…

Machine Learning · Computer Science 2025-02-13 Zhuangwei Shi

We introduce the concept of quotient-convergence for sequences of submodular set functions, providing, among others, a new framework for the study of convergence of matroids through their rank functions. Extending the limit theory of…

Combinatorics · Mathematics 2024-06-17 Kristóf Bérczi , Márton Borbényi , László Lovász , László Márton Tóth

In this paper, we propose scalable methods for maximizing a regularized submodular function $f = g - \ell$ expressed as the difference between a monotone submodular function $g$ and a modular function $\ell$. Indeed, submodularity is…

Machine Learning · Computer Science 2020-02-11 Ehsan Kazemi , Shervin Minaee , Moran Feldman , Amin Karbasi

We consider log-supermodular models on binary variables, which are probabilistic models with negative log-densities which are submodular. These models provide probabilistic interpretations of common combinatorial optimization tasks such as…

Machine Learning · Statistics 2016-08-19 Tatiana Shpakova , Francis Bach

Many practical techniques for probabilistic inference require a sequence of distributions that interpolate between a tractable distribution and an intractable distribution of interest. Usually, the sequences used are simple, e.g., based on…

Artificial Intelligence · Computer Science 2015-09-11 Andreas Stuhlmüller , Robert X. D. Hawkins , N. Siddharth , Noah D. Goodman

This paper provides a unifying view of a wide range of problems of interest in machine learning by framing them as the minimization of functionals defined on the space of probability measures. In particular, we show that generative…

Machine Learning · Computer Science 2019-05-21 Casey Chu , Jose Blanchet , Peter Glynn

Probabilistic graphical models combine the graph theory and probability theory to give a multivariate statistical modeling. They provide a unified description of uncertainty using probability and complexity using the graphical model.…

Machine Learning · Statistics 2011-11-30 Yang Zhou

Graph neural networks (GNNs) have become compelling models designed to perform learning and inference on graph-structured data. However, little work has been done to understand the fundamental limitations of GNNs for scaling to larger…

Machine Learning · Computer Science 2023-10-27 Hyungeun Lee , Kijung Yoon

Exponential random graph models (ERGMs) are a widely used framework for network data, enabling hypothesis testing on the structural mechanisms underlying observed networks. Bayesian ERGMs provide principled uncertainty quantification and…

Methodology · Statistics 2026-05-26 Alberto Caimo , Isabella Gollini

Deep Models are increasingly becoming prevalent in summarization problems (e.g. document, video and images) due to their ability to learn complex feature interactions and representations. However, they do not model characteristics such as…

Machine Learning · Computer Science 2020-10-20 Suraj Kothawade , Jiten Girdhar , Chandrashekhar Lavania , Rishabh Iyer

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Linear mixed-effects models are widely used in analyzing clustered or repeated measures data. We propose a quasi-likelihood approach for estimation and inference of the unknown parameters in linear mixed-effects models with high-dimensional…

Methodology · Statistics 2021-03-10 Sai Li , Tony T. Cai , Hongzhe Li

Combining additive models and neural networks allows to broaden the scope of statistical regression and extend deep learning-based approaches by interpretable structured additive predictors at the same time. Existing attempts uniting the…

Machine Learning · Statistics 2022-07-12 David Rügamer , Chris Kolb , Nadja Klein

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…

Machine Learning · Statistics 2019-06-10 Maria I. Gorinova , Dave Moore , Matthew D. Hoffman