English
Related papers

Related papers: Error bounds revisited

200 papers

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error…

Machine Learning · Computer Science 2016-09-13 Steve Hanneke

We discuss error identities for two classes of free boundary problems generated by obstacles. The identities suggest true forms of the respective error measures which consist of two parts: standard energy norm and a certain nonlinear…

Analysis of PDEs · Mathematics 2017-10-24 Sergey Repin , Jan Valdman

In this paper, we use a Banach fixed point theorem to obtain suficient conditions satisfying the convergence and exponential convergence of solutions for the linear system of advanced differential equations. The considered system with…

Classical Analysis and ODEs · Mathematics 2020-06-25 Mouataz Billah Mesmouli

We present a brief survey of existing mistake bounds and introduce novel bounds for the Perceptron or the kernel Perceptron algorithm. Our novel bounds generalize beyond standard margin-loss type bounds, allow for any convex and Lipschitz…

Machine Learning · Computer Science 2013-07-24 Mehryar Mohri , Afshin Rostamizadeh

In this paper we prove the necessity of the main sufficient condition of Meinardus for sub exponential rate of growth of the number of structures, having multiplicative generating functions of a general form and establish a new necessary…

Combinatorics · Mathematics 2017-06-28 Boris Granovsky

In this paper we consider variational regularization methods for inverse problems with large noise that is in general unbounded in the image space of the forward operator. We introduce a Banach space setting that allows to define a…

Numerical Analysis · Mathematics 2018-02-09 Martin Burger , Tapio Helin , Hanne Kekkonen

Error bounds are a requisite for trusting or distrusting solutions in an informed way. Until recently, provable error bounds in the absence of constraint qualifications were unattainable for many classes of cones that do not admit…

Optimization and Control · Mathematics 2024-07-19 Ying Lin , Scott B. Lindstrom , Bruno F. Lourenço , Ting Kei Pong

This paper focuses on second-order necessary optimality conditions for constrained optimization problems on Banach spaces. For problems in the classical setting, where the objective function is $C^2$-smooth, we show that strengthened…

Optimization and Control · Mathematics 2020-07-30 Duong Thi Viet An , Nguyen Dong Yen

We discuss initial-boundary value problems of arbitrary spatial order subject to arbitrary boundary conditions. We formalise the concept of the conditioning of such a problem and show that it represents a necessary criterion for…

Analysis of PDEs · Mathematics 2012-12-24 David A. Smith

Estimation of solution norms and stability for time-dependent nonlinear systems is ubiquitous in numerous applied and control problems. Yet, practically valuable results are rare in this area. This paper develops a novel approach, which…

Dynamical Systems · Mathematics 2018-08-29 Mark A. Pinsky , Steve Koblik

We prove weighted estimates for singular integral operators which operate on function spaces on a half-line. The class of admissible weights includes Muckenhoupt weights and weights satisfying Sawyer's one-sided conditions. The kernels of…

Classical Analysis and ODEs · Mathematics 2014-10-15 Ralph Chill , Sebastian Krol

I argue that regularizing terms in standard regression methods not only help against overfitting finite data, but sometimes also yield better causal models in the infinite sample regime. I first consider a multi-dimensional variable…

Machine Learning · Statistics 2019-07-01 Dominik Janzing

We study an abstract class of autonomous differential inclusions in Hilbert spaces and show the well-posedness and causality, by establishing the operators involved as maximal monotone operators in time and space. Then the proof of the…

Analysis of PDEs · Mathematics 2013-05-28 Sascha Trostorff

Boundary value problem for complete second order elliptic equation is considered in Banach space. The equation and boundary conditions involve a small and spectral parameter. The uniform L_{p}-regularity properties with respect to space…

Analysis of PDEs · Mathematics 2017-06-06 Veli Shakhmurov

The paper proposes a new bootstrap approach to the Pesaran, Shin and Smith's bound tests in a conditional equilibrium correction model with the aim to overcome some typical drawbacks of the latter, such as inconclusive inference and…

Econometrics · Economics 2022-04-12 Stefano Bertelli , Gianmarco Vacca , Maria Grazia Zoia

The laws of quantum mechanics place fundamental limits on the accuracy of measurements and therefore on the estimation of unknown parameters of a quantum system. In this work, we prove lower bounds on the size of confidence regions reported…

Quantum Physics · Physics 2014-12-23 Michael Walter , Joseph M. Renes

Generalized nonlinear programming is considered without any convexity assumption, capturing a variety of problems that include nonsmooth objectives, combinatorial structures, and set-membership nonlinear constraints. We extend the augmented…

Optimization and Control · Mathematics 2024-04-02 Alberto De Marchi

This paper deals with some classes of Kirchhoff type problems on a double phase setting and with nonlinear boundary conditions. Under general assumptions, we provide multiplicity results for such problems in the case when the perturbations…

Analysis of PDEs · Mathematics 2021-12-16 Alessio Fiscella , Greta Marino , Andrea Pinamonti , Simone Verzellesi

This paper investigates advanced notions of lineability and spaceability within the frameworks of sequence spaces and operator ideals. We propose the notion of \emph{Standard Sequence Classes} to provide an environment that unifies numerous…

Functional Analysis · Mathematics 2026-02-12 Nacib G. Albuquerque , Jamilson R. Campos , Luiz Felipe P. Sousa

Constructing confidence intervals that are simultaneously valid across a class of estimates is central to tasks such as multiple mean estimation, generalization guarantees, and adaptive experimental design. We frame this as an ``error…

Machine Learning · Computer Science 2026-02-05 Sanath Kumar Krishnamurthy , Anna Lyubarskaja , Emma Brunskill , Susan Athey