English
Related papers

Related papers: Density estimation for shift-invariant multidimens…

200 papers

Given i.i.d samples from some unknown continuous density on hyper-rectangle $[0, 1]^d$, we attempt to learn a piecewise constant function that approximates this underlying density non-parametrically. Our density estimate is defined on a…

Machine Learning · Statistics 2015-09-24 Kun Yang , Hao Su , Wing Hung Wang

We study the {\em robust proper learning} of univariate log-concave distributions (over continuous and discrete domains). Given a set of samples drawn from an unknown target distribution, we want to compute a log-concave hypothesis…

Data Structures and Algorithms · Computer Science 2016-06-10 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Learning robust models under distribution shifts between training and test datasets is a fundamental challenge in machine learning. While learning invariant features across environments is a popular approach, it often assumes that these…

Machine Learning · Computer Science 2025-09-15 Taero Kim , Subeen Park , Sungjun Lim , Yonghan Jung , Krikamol Muandet , Kyungwoo Song

Covariate-shift generalization, a typical case in out-of-distribution (OOD) generalization, requires a good performance on the unknown test distribution, which varies from the accessible training distribution in the form of covariate shift.…

Machine Learning · Computer Science 2023-10-18 Renzhe Xu , Xingxuan Zhang , Zheyan Shen , Tong Zhang , Peng Cui

Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of…

Machine Learning · Computer Science 2024-06-07 Yair Schiff , Zhong Yi Wan , Jeffrey B. Parker , Stephan Hoyer , Volodymyr Kuleshov , Fei Sha , Leonardo Zepeda-Núñez

We study nonparametric density estimation in non-stationary drift settings. Given a sequence of independent samples taken from a distribution that gradually changes in time, the goal is to compute the best estimate for the current…

Machine Learning · Computer Science 2023-10-31 Alessio Mazzetto , Eli Upfal

Dynamic decision-making under distributional shifts is of fundamental interest in theory and applications of reinforcement learning: The distribution of the environment in which the data is collected can differ from that of the environment…

Machine Learning · Computer Science 2024-09-05 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. The first contribution of the paper is to extend…

Machine Learning · Statistics 2020-10-20 Gwendoline De Bie , Herilalaina Rakotoarison , Gabriel Peyré , Michèle Sebag

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Yen-Chang Hsu , Yilin Shen , Hongxia Jin , Zsolt Kira

The density ratio is an important metric for evaluating the relative likelihood of two probability distributions, with extensive applications in statistics and machine learning. However, existing estimation theories for density ratios often…

Machine Learning · Statistics 2025-04-03 Shuntuo Xu , Zhou Yu , Jian Huang

Recent advances have revealed that the rate of convergence of the expected test error in deep supervised learning decays as a function of the intrinsic dimension and not the dimension $d$ of the input space. Existing literature defines this…

Machine Learning · Statistics 2024-12-16 Saptarshi Chakraborty , Peter L. Bartlett

While deep neural networks have made remarkable progress in various vision tasks, their performance typically deteriorates when tested in out-of-distribution (OOD) scenarios. Many OOD methods focus on extracting domain-invariant features…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Qiaowei Miao , Yawei Luo , Yi Yang

A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. While in general hard to compute, here we provide the first set of provably efficient algorithms for testing…

Data Structures and Algorithms · Computer Science 2024-06-14 Gautam Chandrasekaran , Adam R. Klivans , Vasilis Kontonis , Konstantinos Stavropoulos , Arsen Vasilyan

The manifold hypothesis asserts that data of interest in high-dimensional ambient spaces, such as image data, lies on unknown low-dimensional submanifolds. Diffusion models (DMs) -- which operate by convolving data with progressively larger…

Machine Learning · Computer Science 2025-10-14 Kin Kwan Leung , Rasa Hosseinzadeh , Gabriel Loaiza-Ganem

Methods for anomaly detection of new physics processes are often limited to low-dimensional spaces due to the difficulty of learning high-dimensional probability densities. Particularly at the constituent level, incorporating desirable…

High Energy Physics - Phenomenology · Physics 2024-03-06 Vinicius Mikuni , Benjamin Nachman

In the field of Machine Learning (ML) and data-driven applications, one of the significant challenge is the change in data distribution between the training and deployment stages, commonly known as distribution shift. This paper outlines…

Machine Learning · Computer Science 2025-07-30 Lakpa Tamang , Mohamed Reda Bouadjenek , Richard Dazeley , Sunil Aryal

Deep learning models lack shift invariance, making them sensitive to input shifts that cause changes in output. While recent techniques seek to address this for images, our findings show that these approaches fail to provide…

Machine Learning · Computer Science 2025-02-28 Berken Utku Demirel , Christian Holz

Consider discrete values of functions shifted by unobserved translation effects, which are independent realizations of a random variable with unknown distribution $\mu$, modeling the variability in the response of each individual. Our aim…

Statistics Theory · Mathematics 2008-12-18 Ismael Castillo , Jean-Michel Loubes

We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper…

Machine Learning · Computer Science 2020-07-23 Hassan Ashtiani , Shai Ben-David , Nick Harvey , Christopher Liaw , Abbas Mehrabian , Yaniv Plan

Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering. However, since…