English
Related papers

Related papers: The Nystr\"om method for convex loss functions

200 papers

We propose a continuous optimization algorithm for the Column Subset Selection Problem (CSSP) and Nystr\"om approximation. The CSSP and Nystr\"om method construct low-rank approximations of matrices based on a predetermined subset of…

Methodology · Statistics 2023-04-20 Anant Mathur , Sarat Moka , Zdravko Botev

Randomized algorithms in numerical linear algebra have proven to be effective in ameliorating issues of scalability when working with large matrices, efficiently producing accurate low-rank approximations. A key remaining challenge,…

Numerical Analysis · Mathematics 2026-01-19 Lorenzo Lazzarino , Katherine J. Pearce , Nathaniel Pritchard

We consider regression with square loss and general classes of functions without the boundedness assumption. We introduce a notion of offset Rademacher complexity that provides a transparent way to study localization both in expectation and…

Machine Learning · Statistics 2020-07-27 Tengyuan Liang , Alexander Rakhlin , Karthik Sridharan

We propose novel randomized optimization methods for high-dimensional convex problems based on restrictions of variables to random subspaces. We consider oblivious and data-adaptive subspaces and study their approximation properties via…

Information Theory · Computer Science 2020-12-15 Jonathan Lacotte , Mert Pilanci

Convex functionals are ubiquitous in applied analysis, appearing as value functions, risk measures, super-hedging prices, and loss functionals in machine learning. In many applications, however, the functional is only observed through…

Functional Analysis · Mathematics 2026-05-12 Anastasis Kratsios

We propose a method to remedy finite sample coverage problems and improve upon the efficiency of commonly employed procedures for the construction of nonparametric confidence intervals in regression kink designs. The proposed interval is…

Econometrics · Economics 2021-11-23 Majed Dodin

Most of the non-asymptotic theoretical work in regression is carried out for the square loss, where estimators can be obtained through closed-form expressions. In this paper, we use and extend tools from the convex optimization literature,…

Machine Learning · Computer Science 2009-10-27 Francis Bach

The Nystrom method is an efficient technique used to speed up large-scale learning applications by generating low-rank approximations. Crucial to the performance of this technique is the assumption that a matrix can be well approximated by…

Machine Learning · Computer Science 2014-08-12 Ameet Talwalkar , Afshin Rostamizadeh

In this paper, we first study nonsmooth steepest descent method for nonsmooth functions defined on Hilbert space and establish the corresponding algorithm by proximal subgradients. Then, we use this algorithm to find stationary points for…

Optimization and Control · Mathematics 2015-02-25 Zhou Wei , Qing Hai He

We generalize the notion of average Lipschitz smoothness proposed by Ashlagi et al. (COLT 2021) by extending it to H\"older smoothness. This measure of the "effective smoothness" of a function is sensitive to the underlying distribution and…

Machine Learning · Computer Science 2023-10-31 Steve Hanneke , Aryeh Kontorovich , Guy Kornowski

It has been observed that certain loss functions can render deep-learning pipelines robust against flaws in the data. In this paper, we support these empirical findings with statistical theory. We especially show that empirical-risk…

Machine Learning · Computer Science 2020-09-15 Johannes Lederer

Kernel methods offer the flexibility to learn complex relationships in modern, large data sets while enjoying strong theoretical guarantees on quality. Unfortunately, these methods typically require cubic running time in the data set size,…

Machine Learning · Statistics 2019-03-01 Raj Agrawal , Trevor Campbell , Jonathan H. Huggins , Tamara Broderick

Many popular learning algorithms (E.g. Regression, Fourier-Transform based algorithms, Kernel SVM and Kernel ridge regression) operate by reducing the problem to a convex optimization problem over a vector space of functions. These methods…

Machine Learning · Computer Science 2014-05-13 Amit Daniely , Nati Linial , Shai Shalev-Shwartz

Randomized methods, such as the randomized SVD (singular value decomposition) and Nystr\"om approximation, are an effective way to compute low-rank approximations of large matrices. Motivated by applications to operator learning, Boull\'e…

Numerical Analysis · Mathematics 2026-02-09 Daniel Kressner , David Persson , André Uschmajew

We provide the first mathematically complete derivation of the Nystr\"om method for low-rank approximation of indefinite kernels and propose an efficient method for finding an approximate eigendecomposition of such kernel matrices. Building…

Machine Learning · Statistics 2019-06-03 Dino Oglic , Thomas Gärtner

We define "decision swap regret" which generalizes both prediction for downstream swap regret and omniprediction, and give algorithms for obtaining it for arbitrary multi-dimensional Lipschitz loss functions in online adversarial settings.…

Machine Learning · Computer Science 2025-02-19 Jiuyao Lu , Aaron Roth , Mirah Shi

The key task of machine learning is to minimize the loss function that measures the model fit to the training data. The numerical methods to do this efficiently depend on the properties of the loss function. The most decisive among these…

Machine Learning · Computer Science 2025-10-31 Tomas Hrycej , Bernhard Bermeitinger , Massimo Pavone , Götz-Henrik Wiegand , Siegfried Handschuh

Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address…

Optimization and Control · Mathematics 2025-09-10 Jingfan Xia , Zhenwei Lin , Qi Deng

The Sinkhorn "distance", a variant of the Wasserstein distance with entropic regularization, is an increasingly popular tool in machine learning and statistical inference. However, the time and memory requirements of standard algorithms for…

Machine Learning · Statistics 2021-11-16 Jason Altschuler , Francis Bach , Alessandro Rudi , Jonathan Niles-Weed

In this paper, we study regression problems over a separable Hilbert space with the square loss, covering non-parametric regression over a reproducing kernel Hilbert space. We investigate a class of spectral/regularized algorithms,…

Machine Learning · Statistics 2022-07-18 Junhong Lin , Alessandro Rudi , Lorenzo Rosasco , Volkan Cevher
‹ Prev 1 3 4 5 6 7 10 Next ›