English
Related papers

Related papers: Model identification and local linear convergence …

200 papers

Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional…

Machine Learning · Statistics 2014-10-29 Niklas Wahlström , Thomas B. Schön , Marc Peter Deisenroth

For various applications, the relations between the dependent and independent variables are highly nonlinear. Consequently, for large scale complex problems, neural networks and regression trees are commonly preferred over linear models…

Machine Learning · Computer Science 2017-05-23 Samet Oymak , Mehrdad Mahdavi , Jiasi Chen

Local feature matching enjoys wide-ranging applications in the realm of computer vision, encompassing domains such as image retrieval, 3D reconstruction, and object recognition. However, challenges persist in improving the accuracy and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shibiao Xu , Shunpeng Chen , Rongtao Xu , Changwei Wang , Peng Lu , Li Guo

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Axis-aligned subspace clustering generally entails searching through enormous numbers of subspaces (feature combinations) and evaluation of cluster quality within each subspace. In this paper, we tackle the problem of identifying subsets of…

Machine Learning · Computer Science 2019-07-17 Ruben Becker , Imane Hafnaoui , Michael E. Houle , Pan Li , Arthur Zimek

Coordinate descent methods have considerable impact in global optimization because global (or, at least, almost global) minimization is affordable for low-dimensional problems. Coordinate descent methods with high-order regularized models…

Optimization and Control · Mathematics 2023-04-28 V. S. Amaral , R. Andreani , E. G. Birgin , D. S. Marcondes , J. M. Martínez

A filament consists of local maximizers of a smooth function $f$ when moving in a certain direction. A filamentary structure is an important feature of the shape of an object and is also considered as an important lower dimensional…

Statistics Theory · Mathematics 2020-03-26 Wei Li , Subhashis Ghosal

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

Machine Learning · Computer Science 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points.…

Machine Learning · Computer Science 2015-03-10 Rong Ge , Furong Huang , Chi Jin , Yang Yuan

A cutting-plane model for a nonsmooth function is the maximum of several first-order expansions centered at different points. Using such a model in a bundle method leads to linear convergence (of serious steps) to a minimum. In smooth…

Optimization and Control · Mathematics 2026-03-26 Bennet Gebken , Michael Ulbrich

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

In this paper, we study the convergence properties of a randomized block-coordinate descent algorithm for the minimization of a composite convex objective function, where the block-coordinates are updated asynchronously and randomly…

Optimization and Control · Mathematics 2023-04-14 Cheik Traoré , Saverio Salzo , Silvia Villa

Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Ali Borji

We prove local convergence of several notable gradient descent algorithms used in machine learning, for which standard stochastic gradient descent theory does not apply directly. This includes, first, online algorithms for recurrent models…

Dynamical Systems · Mathematics 2021-01-11 Pierre-Yves Massé , Yann Ollivier

Simultaneous variable selection and robust data fitting are important aspects of many mathematical modelling projects and a wide array of optimisation tools and techniques exist to support them. When the intention is to embed this…

Mathematical Software · Computer Science 2025-10-28 Stephen Michael Wright

We contribute to the growing body of knowledge on more powerful and adaptive stepsizes for convex optimization, empowered by local curvature information. We do not go the route of fully-fledged second-order methods which require the…

Optimization and Control · Mathematics 2024-05-28 Peter Richtárik , Simone Maria Giancola , Dymitr Lubczyk , Robin Yadav

Linear mixture models have proven very useful in a plethora of applications, e.g., topic modeling, clustering, and source separation. As a critical aspect of the linear mixture models, identifiability of the model parameters is…

Machine Learning · Computer Science 2021-02-24 Bo Yang , Xiao Fu , Nicholas D. Sidiropoulos , Kejun Huang

Deep neural nets typically perform end-to-end backpropagation to learn the weights, a procedure that creates synchronization constraints in the weight update step across layers and is not biologically plausible. Recent advances in…

Machine Learning · Computer Science 2020-12-01 Yuwen Xiong , Mengye Ren , Raquel Urtasun

This paper considers the analysis of continuous time gradient-based optimization algorithms through the lens of nonlinear contraction theory. It demonstrates that in the case of a time-invariant objective, most elementary results on…

Optimization and Control · Mathematics 2022-12-23 Patrick M. Wensing , Jean-Jacques E. Slotine

The usual approach to developing and analyzing first-order methods for non-smooth (stochastic or deterministic) convex optimization assumes that the objective function is uniformly Lipschitz continuous with parameter $M_f$. However, in many…

Optimization and Control · Mathematics 2018-08-15 Haihao Lu