English
Related papers

Related papers: A Coordinate-Free Construction of Scalable Natural…

200 papers

Adaptive regularization methods that exploit more than the diagonal entries exhibit state of the art performance for many tasks, but can be prohibitive in terms of memory and running time. We find the spectra of the Kronecker-factored…

Machine Learning · Statistics 2023-10-18 Vladimir Feinberg , Xinyi Chen , Y. Jennifer Sun , Rohan Anil , Elad Hazan

Quasar-convex functions form a broad nonconvex class with applications to linear dynamical systems, generalized linear models, and Riemannian optimization, among others. Current nearly optimal algorithms work only in affine spaces due to…

Optimization and Control · Mathematics 2026-04-01 David Martínez-Rubio

Existing methods of pruning deep neural networks focus on removing unnecessary parameters of the trained network and fine tuning the model afterwards to find a good solution that recovers the initial performance of the trained model. Unlike…

Machine Learning · Computer Science 2021-11-17 Abdolghani Ebrahimi , Diego Klabjan

Optimal statistical decisions should transcend the language used to describe them. Yet, how do we guarantee that the choice of coordinates - the parameterisation of an optimisation problem - does not subtly dictate the solution? This paper…

Other Computer Science · Computer Science 2025-05-06 William Cook

There is an increasing convergence between biologically plausible computational models of inference and learning with local update rules and the global gradient-based optimization of neural network models employed in machine learning. One…

Machine Learning · Computer Science 2021-11-16 Andre Ofner , Raihan Kabir Ratul , Suhita Ghosh , Sebastian Stober

We study the problem of estimating a manifold from random samples. In particular, we consider piecewise constant and piecewise linear estimators induced by k-means and k-flats, and analyze their performance. We extend previous results for…

Machine Learning · Computer Science 2015-03-20 Guillermo D. Canas , Tomaso Poggio , Lorenzo Rosasco

Coordinate descent (CD) algorithms have become the method of choice for solving a number of optimization problems in machine learning. They are particularly popular for training linear models, including linear support vector machine…

Machine Learning · Statistics 2014-01-16 Tobias Glasmachers , Ürün Dogan

With a computationally efficient approximation of the second-order information, natural gradient methods have been successful in solving large-scale structured optimization problems. We study the natural gradient methods for the large-scale…

Optimization and Control · Mathematics 2023-03-20 Jiang Hu , Kangkang Deng , Na Li , Quanzheng Li

Gradient descent and its variants are de facto standard algorithms for training machine learning models. As gradient descent is sensitive to its hyperparameters, we need to tune the hyperparameters carefully using a grid search. However,…

Machine Learning · Computer Science 2024-11-01 Yuki Takezawa , Han Bao , Ryoma Sato , Kenta Niwa , Makoto Yamada

Recent studies have shown that many nonconvex machine learning problems satisfy a generalized-smooth condition that extends beyond traditional smooth nonconvex optimization. However, the existing algorithms are not fully adapted to such…

Optimization and Control · Mathematics 2025-10-03 Yufeng Yang , Erin Tripp , Yifan Sun , Shaofeng Zou , Yi Zhou

This paper introduces an iterative algorithm for training nonparametric additive models that enjoys favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient…

Machine Learning · Statistics 2026-01-01 Xin Chen , Jason M. Klusowski

The move from hand-designed to learned optimizers in machine learning has been quite successful for gradient-based and -free optimizers. When facing a constrained problem, however, maintaining feasibility typically requires a projection…

Machine Learning · Computer Science 2018-07-31 Patrick Schramowski , Christian Bauckhage , Kristian Kersting

We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable,…

Neural and Evolutionary Computing · Computer Science 2015-11-24 Yann Ollivier , Corentin Tallec , Guillaume Charpiat

We present a Riemannian optimization framework for Hartree-Fock theory formulated directly in the Sobolev space $H^1$. The orthonormality constraints are interpreted geometrically via infinite-dimensional Stiefel and Grassmann manifolds…

Quantum Physics · Physics 2026-03-18 Evgueni Dinvay

Gradient-based methods are well-suited for derivative-free optimization (DFO), where finite-difference (FD) estimates are commonly used as gradient surrogates. Traditional stochastic approximation methods, such as Kiefer-Wolfowitz (KW) and…

Optimization and Control · Mathematics 2025-03-03 Guo Liang , Guangwu Liu , Kun Zhang

We present a stochastic descent algorithm for unconstrained optimization that is particularly efficient when the objective function is slow to evaluate and gradients are not easily obtained, as in some PDE-constrained optimization and…

Optimization and Control · Mathematics 2024-07-08 David Kozak , Stephen Becker , Alireza Doostan , Luis Tenorio

Gradient descent with momentum has been widely applied in various signal processing and machine learning tasks, demonstrating a notable empirical advantage over standard gradient descent. However, momentum-based distributed Riemannian…

Optimization and Control · Mathematics 2026-02-17 Jun Chen , Tianyi Zhu , Haishan Ye , Lina Liu , Guang Dai , Yong Liu , Yunliang Jiang , Ivor W. Tsang

The set of functions parameterized by a linear fully-connected neural network is a determinantal variety. We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group. Examples of such…

Machine Learning · Computer Science 2025-01-13 Kathlén Kohn , Anna-Laura Sattelberger , Vahid Shahverdi

We generate correlated scale-free networks in the configuration model through a new rewiring algorithm which allows to tune the Newman assortativity coefficient $r$ and the average degree of the nearest neighbors $K$ (in the range $-1\le r…

Physics and Society · Physics 2020-06-17 M. L. Bertotti , G. Modanese

We define a class of "optimal" coordinate systems by requiring that the deviation from an exact Robertson-Walker metric is "as small as possible" within a given four dimensional volume. The optimization is performed by minimizing several…

General Relativity and Quantum Cosmology · Physics 2011-11-28 Dieter Gromes