English
Related papers

Related papers: Set structured global empirical risk minimizers ar…

200 papers

Snapshot back-ended reduced basis methods for dynamical systems commonly rely on the singular value decomposition of a matrix whose columns are high-fidelity solution vectors. An alternative basis generation framework is developed here. The…

Numerical Analysis · Mathematics 2020-05-05 Fotios Kasolis , Markus Clemens

Parameter-efficient fine-tuning (PEFT) has become a popular way to adapt large pre-trained models to new tasks. Most PEFT methods update only a small subset of parameters while freezing the rest, avoiding redundant computation. As they…

Machine Learning · Computer Science 2025-08-25 Sungmin Kang , Jisoo Kim , Salman Avestimehr , Sunwoo Lee

We lift important results about universally typical sets, typically sampled sets, and empirical entropy estimation in the theory of samplings of discrete ergodic information sources from the usual one-dimensional discrete-time setting to a…

Information Theory · Computer Science 2013-11-13 Tyll Krueger , Guido Montufar , Ruedi Seiler , Rainer Siegmund-Schultze

Entropy estimation is a fundamental problem in information theory that has applications in various fields, including physics, biology, and computer science. Estimating the entropy of discrete sequences can be challenging due to limited data…

Statistical Mechanics · Physics 2024-01-18 Juan De Gregorio , David Sanchez , Raul Toral

Weight optimization of frame structures with continuous cross-section parametrization is a challenging non-convex problem that has traditionally been solved by local optimization techniques. Here, we exploit its inherent semi-algebraic…

Optimization and Control · Mathematics 2025-01-29 Marek Tyburec , Michal Kočvara , Martin Kružík

We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on $n$ i.i.d. samples are known to have lower accuracy than the classical $n^{- \frac{1}{2}}$ error. We investigate…

Statistics Theory · Mathematics 2021-11-17 Raaz Dwivedi , Nhat Ho , Koulik Khamaru , Martin J. Wainwright , Michael I. Jordan , Bin Yu

Understanding the structural complexity and predictability of complex networks is a central challenge in network science. Although recent studies have revealed a relationship between compression-based entropy and link prediction…

Social and Information Networks · Computer Science 2025-10-14 Sebastián Brzovic , Cristóbal Rojas , Andrés Abeliuk

The maximum entropy principle (MEP) is a method for obtaining the most likely distribution functions of observables from statistical systems, by maximizing entropy under constraints. The MEP has found hundreds of applications in ergodic and…

Classical Physics · Physics 2016-10-03 Rudolf Hanel , Stefan Thurner , Murray Gell-Mann

As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the training data. In this…

Machine Learning · Computer Science 2021-01-06 Jaeho Lee , Maxim Raginsky

Empirical risk minimization (ERM) can be computationally expensive, with standard solvers scaling poorly even in the convex setting. We propose a novel lossless compression framework for convex ERM based on color refinement, extending prior…

Optimization and Control · Mathematics 2026-02-03 Bryan Zhu , Ziang Chen

In this paper, we study the entropy of a hard random geometric graph (RGG), a commonly used model for spatial networks, where the connectivity is governed by the distances between the nodes. Formally, given a connection range $r$, a hard…

Information Theory · Computer Science 2026-01-19 Praneeth Kumar Vippathalla , Justin P. Coon , Mihai-Alin Badiu

In this paper, we clarify the relations between the existing sets of regularity conditions for convergence rates of nonparametric indirect regression (NPIR) and nonparametric instrumental variables (NPIV) regression models. We establish…

Statistics Theory · Mathematics 2007-09-14 Xiaohong Chen , Markus Reiss

By locally encoding raw data into intermediate features, collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data to cloud servers. However, recent studies have revealed that…

Machine Learning · Computer Science 2025-04-04 Song Xia , Yi Yu , Wenhan Yang , Meiwen Ding , Zhuo Chen , Ling-Yu Duan , Alex C. Kot , Xudong Jiang

Finite mixture models are widely used in econometric analyses to capture unobserved heterogeneity. This paper shows that maximum likelihood estimation of finite mixtures of parametric densities can suffer from substantial finite-sample bias…

Methodology · Statistics 2026-02-04 Raphaël Langevin

Mixture of linear regression is well studied in statistics and machine learning, where the data points are generated probabilistically using $k$ linear models. Algorithms like Expectation Maximization (EM) may be used to recover the ground…

Machine Learning · Computer Science 2026-04-08 Avishek Ghosh

Structured prediction tasks in machine learning involve the simultaneous prediction of multiple labels. This is typically done by maximizing a score function on the space of labels, which decomposes as a sum of pairwise elements, each…

Machine Learning · Computer Science 2014-09-23 Amir Globerson , Tim Roughgarden , David Sontag , Cafer Yildirim

Entropy solutions have been widely accepted as the suitable solution framework for systems of conservation laws in several space dimensions. However, recent results in \cite{CDL1,CDL2} have demonstrated that entropy solutions may not be…

Numerical Analysis · Mathematics 2018-08-01 Ulrik S. Fjordholm , Roger Käppeli , Siddhartha Mishra , Eitan Tadmor

We provide a general theory of the expectation-maximization (EM) algorithm for inferring high dimensional latent variable models. In particular, we make two contributions: (i) For parameter estimation, we propose a novel high dimensional EM…

Machine Learning · Statistics 2015-01-28 Zhaoran Wang , Quanquan Gu , Yang Ning , Han Liu

We study the convergence of the Expectation-Maximization (EM) algorithm for mixtures of linear regressions with an arbitrary number $k$ of components. We show that as long as signal-to-noise ratio (SNR) is $\tilde{\Omega}(k)$,…

Machine Learning · Computer Science 2019-11-27 Jeongyeol Kwon , Constantine Caramanis

This paper establishes the minimum entropy principle (MEP) for the relativistic Euler equations with a broad class of equations of state (EOSs) and addresses the challenge of preserving the local version of the discovered MEP in high-order…

Numerical Analysis · Mathematics 2025-03-18 Shumo Cui , Kailiang Wu , Linfeng Xu
‹ Prev 1 8 9 10 Next ›