English
Related papers

Related papers: The knee-jerk mapping

200 papers

Deep learning optimizers are often motivated through a mix of convex and approximate second-order theory. We select three such methods -- Adam, Shampoo and Prodigy -- and argue that each method can instead be understood as a squarely…

Machine Learning · Computer Science 2024-12-09 Jeremy Bernstein , Laker Newhouse

The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this relaxation forms a manifold, which we call the Relaxed…

Machine Learning · Computer Science 2025-04-14 Jinghui Yuan , Fangyuan Xie , Feiping Nie , Xuelong Li

Maximum likelihood estimation (MLE) is one of the most important methods in machine learning, and the expectation-maximization (EM) algorithm is often used to obtain maximum likelihood estimates. However, EM heavily depends on initial…

Machine Learning · Statistics 2017-11-21 Hideyuki Miyahara , Koji Tsumura , Yuki Sughiyama

We introduce motions as real six-dimensional vectors. A motion means a rotation and a translation. We define a motion operator which maps unit dual quaternions to motions, and a UDQ operator which maps motions to unit dual quaternions. By…

Optimization and Control · Mathematics 2022-12-29 Liqun Qi

Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a…

Machine Learning · Computer Science 2021-12-16 Kevin Huang , Sahin Lale , Ugo Rosolia , Yuanyuan Shi , Anima Anandkumar

Optimization theory serves as a pivotal scientific instrument for achieving optimal system performance, with its origins in economic applications to identify the best investment strategies for maximizing benefits. Over the centuries, from…

Machine Learning · Computer Science 2024-09-10 Yuhan Ma , Dan Sun , Erdi Gao , Ningjing Sang , Iris Li , Guanming Huang

The expectation--maximization (EM) algorithm combines global monotonicity, local linear convergence, and strong practical robustness, but these features are usually analyzed separately. Global descent is nonlinear, whereas local convergence…

Machine Learning · Statistics 2026-05-11 Qiao Wang

Zhu and Melnykov (2018) develop a model to fit mixture models when the components are derived from the Manly transformation. Their EM algorithm utilizes Nelder-Mead optimization in the M-step to update the skew parameter,…

Machine Learning · Statistics 2025-08-04 Katharine M. Clark , Paul D. McNicholas

The Expectation-Maximization (EM) algorithm is one of the most popular methods used to solve the problem of parametric distribution-based clustering in unsupervised learning. In this paper, we propose to analyze a generalized EM (GEM)…

Optimization and Control · Mathematics 2021-05-19 Sarthak Chatterjee , Orlando Romero , Sérgio Pequito

Bayesian networks (BN) are used in a big range of applications but they have one issue concerning parameter learning. In real application, training data are always incomplete or some nodes are hidden. To deal with this problem many learning…

Artificial Intelligence · Computer Science 2012-04-12 Fradj Ben Lamine , Karim Kalti , Mohamed Ali Mahjoub

An ordered $r$-matching is an $r$-uniform hypergraph matching equipped with an ordering on its vertices. These objects can be viewed as natural generalisations of $r$-dimensional orders. The theory of ordered 2-matchings is well-developed…

Combinatorics · Mathematics 2025-03-19 Michael Anastos , Zhihan Jin , Matthew Kwan , Benny Sudakov

We present a novel probabilistic finite element method (FEM) for the solution and uncertainty quantification of elliptic partial differential equations based on random meshes, which we call random mesh FEM (RM-FEM). Our methodology allows…

Numerical Analysis · Mathematics 2021-06-17 Assyr Abdulle , Giacomo Garegnani

EM algorithm is a convenient tool for maximum likelihood model fitting when the data are incomplete or when there are latent variables or hidden states. In this review article we explain that EM algorithm is a natural computational scheme…

Methodology · Statistics 2011-04-13 Zhangzhang Si , Haifeng Gong , Song-Chun Zhu , Ying Nian Wu

In this paper, we analyze the celebrated EM algorithm from the point of view of proximal point algorithms. More precisely, we study a new type of generalization of the EM procedure introduced in \cite{Chretien&Hero:98} and called…

Computation · Statistics 2012-01-31 Stéphane Chrétien , Alfred O. Hero

In this paper, we firstly give a brief introduction of expectation maximization (EM) algorithm, and then discuss the initial value sensitivity of expectation maximization algorithm. Subsequently, we give a short proof of EM's convergence.…

Machine Learning · Computer Science 2013-05-06 Fuqiang Chen

We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Dongki Jung , Jaehoon Choi , Yonghan Lee , Somi Jeong , Taejae Lee , Dinesh Manocha , Suyong Yeon

The Expectation-Maximization (EM) algorithm (Dempster, Laird and Rubin, 1977) is a popular method for computing maximum likelihood estimates (MLEs) in problems with missing data. Each iteration of the al- gorithm formally consists of an…

Statistics Theory · Mathematics 2012-06-22 Ronald C. Neath

The notion of best approximation mapping (BAM) with respect to a closed affine subspace in finite-dimensional space was introduced by Behling, Bello Cruz and Santos to show the linear convergence of the block-wise circumcentered-reflection…

Optimization and Control · Mathematics 2020-06-05 Heinz H. Bauschke , Hui Ouyang , Xianfu Wang

We develop a computationally tractable method for estimating the optimal map between two distributions over $\mathbb{R}^d$ with rigorous finite-sample guarantees. Leveraging an entropic version of Brenier's theorem, we show that our…

Statistics Theory · Mathematics 2024-05-14 Aram-Alexandre Pooladian , Jonathan Niles-Weed

A common way to train neural networks is the Backpropagation. This algorithm includes a gradient descent method, which needs an adaptive step size. In the area of neural networks, the ADAM-Optimizer is one of the most popular adaptive step…

Machine Learning · Computer Science 2018-04-30 Sebastian Bock , Josef Goppold , Martin Weiß