English
Related papers

Related papers: Unexpected properties of bandwidth choice when smo…

200 papers

Semisupervised methods inevitably invoke some assumption that links the marginal distribution of the features to the regression function of the label. Most commonly, the cluster or manifold assumptions are used which imply that the…

Statistics Theory · Mathematics 2011-12-02 Martin Azizyan , Aarti Singh , Larry Wasserman

Randomized smoothing is currently considered the state-of-the-art method to obtain certifiably robust classifiers. Despite its remarkable performance, the method is associated with various serious problems such as "certified accuracy…

Machine Learning · Computer Science 2024-03-11 Peter Súkeník , Aleksei Kuvshinov , Stephan Günnemann

Neural autoregressive sequence models smear the probability among many possible sequences including degenerate ones, such as empty or repetitive sequences. In this work, we tackle one specific case where the model assigns a high probability…

Machine Learning · Computer Science 2021-12-23 Ilia Kulikov , Maksim Eremeev , Kyunghyun Cho

We generalize the technique of smoothed analysis to distributed algorithms in dynamic network models. Whereas standard smoothed analysis studies the impact of small random perturbations of input values on algorithm performance metrics,…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-08-17 Michael Dinitz , Jeremy T. Fineman , Seth Gilbert , Calvin Newport

This paper studies the estimation of smooth functionals $f(\theta)$ of a mean parameter $\theta = \mathbb{E}_P[W]$ for a distribution $P$ on a general Banach space. We propose a cross-fitted estimator based on a single sample splitting and…

Statistics Theory · Mathematics 2026-04-03 Woonyoung Chang , Arun Kumar Kuchibhotla

Snow density estimates as a function of depth are used for understanding climate processes, evaluating water accumulation trends in polar regions, and estimating glacier mass balances. The common and interpretable physically-derived…

Methodology · Statistics 2021-06-22 Philip White , Durban Keeler , Daniel Sheanshang , Summer Rupper

This paper discusses a general framework for smoothing parameter estimation for models with regular likelihoods constructed in terms of unknown smooth functions of covariates. Gaussian random effects and parametric terms may also be…

Methodology · Statistics 2016-05-10 Simon N. Wood , Natalya Pya , Benjamin Säfken

The notion of data depth has long been in use to obtain robust location and scale estimates in a multivariate setting. The depth of an observation is a measure of its centrality, with respect to a data set or a distribution. The data depths…

Methodology · Statistics 2009-09-29 Sara López-Pintado , Rebecka Jornsten

Deep learning techniques have achieved remarkable performance in wide-ranging tasks. However, when trained on privacy-sensitive datasets, the model parameters may expose private information in training data. Prior attempts for…

Machine Learning · Computer Science 2021-06-22 Wenxiao Wang , Tianhao Wang , Lun Wang , Nanqing Luo , Pan Zhou , Dawn Song , Ruoxi Jia

The order of smoothness chosen in nonparametric estimation problems is critical. This choice balances the tradeoff between model parsimony and data overfitting. The most common approach used in this context is cross-validation. However,…

Methodology · Statistics 2015-10-13 Daniel Taylor-Rodriguez , Sujit Ghosh

A variance reduction technique in nonparametric smoothing is proposed: at each point of estimation, form a linear combination of a preliminary estimator evaluated at nearby points with the coefficients specified so that the asymptotic bias…

Statistics Theory · Mathematics 2007-08-22 Ming-Yen Cheng , Liang Peng , Jyh-Shyang Wu

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider…

Machine Learning · Statistics 2022-06-08 Peter L. Bartlett , Philip M. Long , Gábor Lugosi , Alexander Tsigler

The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite…

Statistics Theory · Mathematics 2021-03-17 Peter L. Bartlett , Andrea Montanari , Alexander Rakhlin

Submodular function optimization has numerous applications in machine learning and data analysis, including data summarization which aims to identify a concise and diverse set of data points from a large dataset. It is important to…

Data Structures and Algorithms · Computer Science 2023-04-11 Shaojie Tang , Jing Yuan , Twumasi Mensah-Boateng

Large-sample data became prevalent as data acquisition became cheaper and easier. While a large sample size has theoretical advantages for many statistical methods, it presents computational challenges. Sketching, or compression, is a…

Machine Learning · Statistics 2020-05-11 Alexander F. Lapanowski , Irina Gaynanova

Big data is ubiquitous in practices, and it has also led to heavy computation burden. To reduce the calculation cost and ensure the effectiveness of parameter estimators, an optimal subset sampling method is proposed to estimate the…

Methodology · Statistics 2023-11-16 Haohui Han , Liya Fu

A natural measure of smoothness of a Boolean function is its sensitivity (the largest number of Hamming neighbors of a point which differ from it in function value). The structure of smooth or equivalently low-sensitivity functions is still…

Computational Complexity · Computer Science 2015-08-12 Parikshit Gopalan , Noam Nisan , Rocco A. Servedio , Kunal Talwar , Avi Wigderson

Graph-based methods have been quite successful in solving unsupervised and semi-supervised learning problems, as they provide a means to capture the underlying geometry of the dataset. It is often desirable for the constructed graph to…

Machine Learning · Computer Science 2019-04-16 Aamir Anis , Aly El Gamal , Salman Avestimehr , Antonio Ortega

Semi-Supervised Learning (SSL) seeks to leverage large amounts of non-annotated data along with the smallest amount possible of annotated data in order to achieve the same level of performance as if all data were annotated. A fruitful…

Machine Learning · Computer Science 2024-05-24 Nikolaos Karaliolios , Hervé Le Borgne , Florian Chabot

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