English
Related papers

Related papers: A Bernstein-type Inequality for Some Mixing Proces…

200 papers

Learning algorithms that divide the data into batches are prevalent in many machine-learning applications, typically offering useful trade-offs between computational efficiency and performance. In this paper, we examine the benefits of…

Machine Learning · Computer Science 2024-09-24 Shahar Stein Ioushua , Inbar Hasidim , Ofer Shayevitz , Meir Feder

In this article, we provide a modification to the Bregman Golden Ratio Algorithm (B-GRAAL). We analyze the B-GRAAL algorithm with a new step size rule, where the step size increases after a certain number of iterations and does not require…

Optimization and Control · Mathematics 2025-03-11 Gourav Kumar , V. Vetrivel

We study the approximation of univariate and multivariate set-valued functions (SVFs) by the adaptation to SVFs of positive samples-based approximation operators for real-valued functions. To this end, we introduce a new weighted average of…

Numerical Analysis · Mathematics 2012-11-29 Shay Kels , Nira Dyn

This paper focuses on learning rate analysis of Nystr\"{o}m regularization with sequential sub-sampling for $\tau$-mixing time series. Using a recently developed Banach-valued Bernstein inequality for $\tau$-mixing sequences and an integral…

Machine Learning · Computer Science 2021-11-16 Zirui Sun , Mingwei Dai , Yao Wang , Shao-Bo Lin

We propose a novel technique for algorithm-selection, applicable to optimisation domains in which there is implicit sequential information encapsulated in the data, e.g., in online bin-packing. Specifically we train two types of recurrent…

Machine Learning · Computer Science 2022-03-28 Mohamad Alissa , Kevin Sim , Emma Hart

In this paper we extend an inequality of Lenglart, L\'epingle and Pratelli \cite[Lemma 1.1]{LLP} to general continuous adapted stochastic processes with values in topology spaces. By this inequality we show Burkholder-Davies-Gundy's…

Probability · Mathematics 2016-06-15 Yingchao Xie , Xicheng Zhang

Problem definition: A key challenge in supervised learning is data scarcity, which can cause prediction models to overfit to the training data and perform poorly out of sample. A contemporary approach to combat overfitting is offered by…

Optimization and Control · Mathematics 2025-10-10 Reza Belbasi , Aras Selvi , Wolfram Wiesemann

We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. Working with bounded and $\pi$-canonical kernels, we show that we can recover the convergence rate of Arcones and Gin{\'e} who proved…

Probability · Mathematics 2022-03-21 Quentin Duchemin , Yohann de Castro , Claire Lacour

In practice, optimization tasks have some structure that allows developing new algorithms for every problem with faster convergence rates. Using the structure of optimization tasks, we can propose algorithms with more optimistic convergence…

Optimization and Control · Mathematics 2020-09-01 Alexander Tyurin

A fundamental problem in numerical analysis and approximation theory is approximating smooth functions by polynomials. A much harder version under recent consideration is to enforce bounds constraints on the approximating polynomial. In…

Numerical Analysis · Mathematics 2021-12-28 Larry Allen , Robert C. Kirby

Many machine learning problems can be framed in the context of estimating functions, and often these are time-dependent functions that are estimated in real-time as observations arrive. Gaussian processes (GPs) are an attractive choice for…

Machine Learning · Statistics 2023-05-09 Michael Minyi Zhang , Bianca Dumitrascu , Sinead A. Williamson , Barbara E. Engelhardt

Classical worst-case optimization theory neither explains the success of optimization in machine learning, nor does it help with step size selection. In this paper we demonstrate the viability and advantages of replacing the classical…

Optimization and Control · Mathematics 2024-10-16 Felix Benning , Leif Döring

Well-calibrated probabilistic regression models are a crucial learning component in robotics applications as datasets grow rapidly and tasks become more complex. Unfortunately, classical regression models are usually either probabilistic…

Machine Learning · Computer Science 2023-09-12 Hany Abdulsamad , Peter Nickl , Pascal Klink , Jan Peters

As an alternative to the well-known methods of "chaining" and "bracketing" that have been developed in the study of random fields, a new method, which is based on a {\em stochastic maximal inequality} derived by using the formula for…

Probability · Mathematics 2017-08-16 Yoichi Nishiyama

Gaussian processes models are widely adopted for nonparameteric/semi-parametric modeling. Identifiability issues occur when the mean model contains polynomials with unknown coefficients. Though resulting prediction is unaffected, this leads…

Methodology · Statistics 2016-11-02 Matthew Plumlee , V. Roshan Joseph

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

Optimization and Control · Mathematics 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

In this work, multiplicative stochasticity is applied to the learning rate of stochastic optimization algorithms, giving rise to stochastic learning-rate schemes. In-expectation theoretical convergence results of Stochastic Gradient Descent…

Optimization and Control · Mathematics 2022-03-22 Theodoros Mamalis , Dusan Stipanovic , Petros Voulgaris

Given a submodular capacity space, we prove the uniform convergence in capacity and also the uniform convergence in the Choquet-mean of order $p\ge1$ with a quantitative estimate, of the multivariate Bernstein polynomials associated to a…

Classical Analysis and ODEs · Mathematics 2020-10-02 Sorin G. Gal , Constantin Niculescu

Training in machine learning generally consists in finding one model, whose parameters minimize a data-dependent loss. Yet, empirical work shows that ensemble learning, an approach in which multiple models are sampled, can improve…

Disordered Systems and Neural Networks · Physics 2026-04-28 Thomas Tulinski , Jorge Fernandez-De-Cossio-Diaz , Simona Cocco , Rémi Monasson

Piecewise $\alpha$-stable Ornstein-Uhlenbeck (OU) processes arising in queue networks usually do not have an explicit dissipation, which makes the related numerical methods such as Euler-Maruyama (EM) scheme more difficult to analyze. We…

Probability · Mathematics 2024-11-11 Xinghu Jin , Guodong Pang , Yu Wang , Lihu Xu