English
Related papers

Related papers: Concentration inequalities for leave-one-out cross…

200 papers

Consider the problem of testing whether the outputs of a large language model (LLM) system change under an arbitrary intervention, such as an input perturbation or changing the model variant. We cannot simply compare two LLM outputs since…

Computation and Language · Computer Science 2025-06-10 Paulius Rauba , Qiyao Wei , Mihaela van der Schaar

Lipschitz Bound Estimation is an effective method of regularizing deep neural networks to make them robust against adversarial attacks. This is useful in a variety of applications ranging from reinforcement learning to autonomous systems.…

Machine Learning · Computer Science 2022-07-18 Sarosij Bose

We deal with the problem of determining an inclusion within an electrical conductor from electrical boundary measurements. Under mild a priori assumptions we establish an optimal stability estimate.

Analysis of PDEs · Mathematics 2007-05-23 Giovanni Alessandrini , Michele Di Cristo

We present a data-driven framework based on Lyapunov theory to provide stability guarantees for a family of hybrid systems. In particular, we are interested in the asymptotic stability of switching linear systems whose switching sequence is…

Systems and Control · Electrical Eng. & Systems 2023-02-13 Adrien Banse , Zheming Wang , Raphaël M. Jungers

Stability selection is a widely adopted resampling-based framework for high-dimensional variable selection. This paper seeks to broaden the use of an established stability estimator to evaluate the overall stability of the stability…

Methodology · Statistics 2025-06-04 Mahdi Nouraie , Samuel Muller

We develop a finite-dimensional sensitivity framework for studying stability in learning systems whose states include representations, parameters, and update variables. The central object is the \emph{Learning Stability Profile}, a…

Machine Learning · Computer Science 2026-05-26 Ronald Katende

We consider outlier-robust and sparse estimation of linear regression coefficients, when the covariates and the noises are contaminated by adversarial outliers and noises are sampled from a heavy-tailed distribution. Our results present…

Statistics Theory · Mathematics 2024-05-27 Takeyuki Sasai , Hironori Fujisawa

Studying unified model averaging estimation for situations with complicated data structures, we propose a novel model averaging method based on cross-validation (MACV). MACV unifies a large class of new and existing model averaging…

Methodology · Statistics 2024-12-16 Dalei Yu , Xinyu Zhang , Hua Liang

In this work, we provide stability estimates for the continuity equation with Sobolev vector fields. The results are inferred from contraction estimates for certain logarithmic Kantorovich--Rubinstein distances. As a by-product, we obtain a…

Analysis of PDEs · Mathematics 2017-01-30 Christian Seis

Extensively evaluating the capabilities of (large) language models is difficult. Rapid development of state-of-the-art models induce benchmark saturation, while creating more challenging datasets is labor-intensive. Inspired by the recent…

Computation and Language · Computer Science 2025-06-02 Alan Sun

Consider the following class of learning schemes: $$\hat{\boldsymbol{\beta}} := \arg\min_{\boldsymbol{\beta}}\;\sum_{j=1}^n \ell(\boldsymbol{x}_j^\top\boldsymbol{\beta}; y_j) + \lambda R(\boldsymbol{\beta}),\qquad\qquad (1) $$ where…

Machine Learning · Statistics 2018-07-10 Shuaiwen Wang , Wenda Zhou , Haihao Lu , Arian Maleki , Vahab Mirrokni

New Vapnik and Chervonenkis type concentration inequalities are derived for the empirical distribution of an independent random sample. Focus is on the maximal deviation over classes of Borel sets within a low probability region. The…

Statistics Theory · Mathematics 2022-04-26 Stéphane Lhaut , Anne Sabourin , Johan Segers

Model selection is a major challenge in non-parametric clustering. There is no universally admitted way to evaluate clustering results for the obvious reason that no ground truth is available. The difficulty to find a universal evaluation…

Machine Learning · Computer Science 2023-05-18 Alex Mourer , Florent Forest , Mustapha Lebbah , Hanane Azzag , Jérôme Lacaille

Recently, there has been substantial interest in statistical guarantees for cross-validation (CV) methods of uncertainty quantification in statistical learning (cf. Barber et al. 2021a, Liang and Barber 2024, Steinberger and Leeb 2023).…

Statistics Theory · Mathematics 2025-05-09 Nicolai Amann , Hannes Leeb , Lukas Steinberger

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

Dynamical Systems · Mathematics 2020-01-22 Mark A. Pinsky , Steve Koblik

Cross-validation is one of the most popular model selection methods in statistics and machine learning. Despite its wide applicability, traditional cross validation methods tend to select overfitting models, due to the ignorance of the…

Methodology · Statistics 2017-12-25 Jing Lei

Cross-validation (CV) is a common method to tune machine learning methods and can be used for model selection in regression as well. Because of the structured nature of small, traditional experimental designs, the literature has warned…

Applications · Statistics 2025-06-18 Maria L. Weese , Byran J. Smucker , David J. Edwards

It is shown that bootstrap approximations of an estimator which is based on a continuous operator from the set of Borel probability measures defined on a compact metric space into a complete separable metric space is stable in the sense of…

Statistics Theory · Mathematics 2011-11-09 Andreas Christmann , Matias Salibian-Barrera , Stefan Van Aelst

Answering a question left open in \cite{MZ2}, we show for general symmetric hyperbolic boundary problems with constant coefficients, including in particular systems with characteristics of variable multiplicity, that the uniform Lopatinski…

Analysis of PDEs · Mathematics 2007-05-23 Olivier Gues , Guy Metivier , Mark Williams , Kevin Zumbrun

In modern data analysis, sparse model selection becomes inevitable once the number of predictors variables is very high. It is well-known that model selection procedures like the Lasso or Boosting tend to overfit on real data. The…

Machine Learning · Computer Science 2022-02-11 Tino Werner
‹ Prev 1 4 5 6 7 8 10 Next ›