English
Related papers

Related papers: Diving into the shallows: a computational perspect…

200 papers

Motivated by the extensive application of approximate gradients in machine learning and optimization, we investigate inexact subgradient methods subject to persistent additive errors. Within a nonconvex semialgebraic framework, assuming…

Optimization and Control · Mathematics 2025-05-14 Jérôme Bolte , Tam Le , Éric Moulines , Edouard Pauwels

We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of…

Statistics Theory · Mathematics 2017-05-31 Taiji Suzuki

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite…

Machine Learning · Computer Science 2025-04-01 Binchuan Qi , Wei Gong , Li Li

Reduced modeling in high-dimensional reproducing kernel Hilbert spaces offers the opportunity to approximate efficiently non-linear dynamics. In this work, we devise an algorithm based on low rank constraint optimization and kernel-based…

Machine Learning · Computer Science 2020-02-23 Patrick Heas , Cedric Herzet , Benoit Combes

The Gaussian kernel plays a central role in machine learning, uncertainty quantification and scattered data approximation, but has received relatively little attention from a numerical analysis standpoint. The basic problem of finding an…

Numerical Analysis · Mathematics 2021-04-02 Toni Karvonen , Chris J. Oates , Mark Girolami

Optimization under structural constraints is typically analyzed through projection or penalty methods, obscuring the geometric mechanism by which constraints shape admissible dynamics. We propose an operator-theoretic formulation in which…

Optimization and Control · Mathematics 2026-03-10 Changkai Li

We propose a deep learning approach for discovering kernels tailored to identifying clusters over sample data. Our neural network produces sample embeddings that are motivated by--and are at least as expressive as--spectral clustering. Our…

Machine Learning · Computer Science 2020-01-03 Chieh Wu , Zulqarnain Khan , Yale Chang , Stratis Ioannidis , Jennifer Dy

Wide neural networks are biased towards learning certain functions, influencing both the rate of convergence of gradient descent (GD) and the functions that are reachable with GD in finite training time. As such, there is a great need for…

Machine Learning · Computer Science 2024-03-21 Amnon Geifman , Daniel Barzilai , Ronen Basri , Meirav Galun

Nonlinear kernels can be approximated using finite-dimensional feature maps for efficient risk minimization. Due to the inherent trade-off between the dimension of the (mapped) feature space and the approximation accuracy, the key problem…

Machine Learning · Computer Science 2018-10-10 Shahin Shahrampour , Vahid Tarokh

This paper explores variants of the subspace iteration algorithm for computing approximate invariant subspaces. The standard subspace iteration approach is revisited and new variants that exploit gradient-type techniques combined with a…

Numerical Analysis · Mathematics 2024-05-14 Foivos Alimisis , Yousef Saad , Bart Vandereycken

We consider stochastic gradient descent (SGD) for least-squares regression with potentially several passes over the data. While several passes have been widely reported to perform practically better in terms of predictive performance on…

Machine Learning · Computer Science 2018-11-26 Loucas Pillaud-Vivien , Alessandro Rudi , Francis Bach

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

Working with any gradient-based machine learning algorithm involves the tedious task of tuning the optimizer's hyperparameters, such as its step size. Recent work has shown how the step size can itself be optimized alongside the model…

Machine Learning · Computer Science 2022-10-18 Kartik Chandra , Audrey Xie , Jonathan Ragan-Kelley , Erik Meijer

A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

We study statistical inverse learning in the context of nonlinear inverse problems under random design. Specifically, we address a class of nonlinear problems by employing gradient descent (GD) and stochastic gradient descent (SGD) with…

Machine Learning · Statistics 2024-12-24 Abhishake , Nicole Mücke , Tapio Helin

Inverse Optimization (IO) is a framework for learning the unknown objective function of an expert decision-maker from a past dataset. In this paper, we extend the hypothesis class of IO objective functions to a reproducing kernel Hilbert…

Machine Learning · Computer Science 2024-11-01 Youyuan Long , Tolga Ok , Pedro Zattoni Scroccaro , Peyman Mohajerin Esfahani

Deep kernel learning aims at designing nonlinear combinations of multiple standard elementary kernels by training deep networks. This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the…

Computer Vision and Pattern Recognition · Computer Science 2018-05-01 Mingyuan Jiu , Hichem Sahbi

To accelerate kernel methods, we propose a near input sparsity time algorithm for sampling the high-dimensional feature space implicitly defined by a kernel transformation. Our main contribution is an importance sampling method for…

Data Structures and Algorithms · Computer Science 2020-07-15 David P. Woodruff , Amir Zandieh

Kernel methods are a popular class of nonlinear predictive models in machine learning. Scalable algorithms for learning kernel models need to be iterative in nature, but convergence can be slow due to poor conditioning. Spectral…

Machine Learning · Statistics 2024-01-26 Amirhesam Abedsoltan , Parthe Pandit , Luis Rademacher , Mikhail Belkin

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak
‹ Prev 1 3 4 5 6 7 10 Next ›