English
Related papers

Related papers: A Concentration Result of Estimating Phi-Divergenc…

200 papers

We consider the problem of learning a discrete distribution in the presence of an $\epsilon$ fraction of malicious data sources. Specifically, we consider the setting where there is some underlying distribution, $p$, and each data source…

Machine Learning · Computer Science 2017-11-23 Mingda Qiao , Gregory Valiant

Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption doesn't generally hold true in a natural setting. Usually, the…

Machine Learning · Computer Science 2021-12-14 Kumud Lakara , Akshat Bhandari , Pratinav Seth , Ujjwal Verma

We consider the problem of performing Bayesian inference in probabilistic models where observations are accompanied by uncertainty, referred to as "uncertain evidence." We explore how to interpret uncertain evidence, and by extension the…

Machine Learning · Statistics 2023-01-27 Andreas Munk , Alexander Mead , Frank Wood

We study the general problem of testing whether an unknown distribution belongs to a specified family of distributions. More specifically, given a distribution family $\mathcal{P}$ and sample access to an unknown discrete distribution…

Data Structures and Algorithms · Computer Science 2017-08-09 Clément L. Canonne , Ilias Diakonikolas , Alistair Stewart

In this report we discuss the treatment of statistical errors in cut efficiencies. The two commonly used methods for the calculation of the errors, Poissonian and Binomial, are shown to be defective. We derive the form of the underlying…

Data Analysis, Statistics and Probability · Physics 2012-05-15 T. Ullrich , Z. Xu

In this paper, we consider one aspect of the problem of applying decision theory to the design of agents that learn how to make decisions under uncertainty. This aspect concerns how an agent can estimate probabilities for the possible…

Artificial Intelligence · Computer Science 2013-03-26 Adam J. Grove , Daphne Koller

Rooted trees with probabilities are used to analyze properties of a variable length code. A bound is derived on the difference between the entropy rates of the code and a memoryless source. The bound is in terms of normalized informational…

Information Theory · Computer Science 2013-10-11 Georg Böcherer , Rana Ali Amjad

The study of mixture models constitutes a large domain of research in statistics. In the first part of this work, we present phi-divergences and the existing methods which produce robust estimators. We are more particularly interested in…

Methodology · Statistics 2016-11-28 Diaa Al Mohamad

Partitioning a set of elements into an unknown number of mutually exclusive subsets is essential in many machine learning problems. However, assigning elements, such as samples in a dataset or neurons in a network layer, to an unknown and…

Machine Learning · Computer Science 2023-11-10 Thomas M. Sutter , Alain Ryser , Joram Liebeskind , Julia E. Vogt

When the data do not conform to the hypothesis of a known sampling-variance, the fitting of a constant to a set of measured values is a long debated problem. Given the data, fitting would require to find what measurand value is the most…

Data Analysis, Statistics and Probability · Physics 2020-07-21 Giovanni Mana , Enrico Massa , Maria Predescu

Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before…

Machine Learning · Computer Science 2021-01-26 Yash Chandak , Shiv Shankar , Philip S. Thomas

We present novel bounds for estimating discrete probability distributions under the $\ell_\infty$ norm. These are nearly optimal in various precise senses, including a kind of instance-optimality. Our data-dependent convergence guarantees…

Statistics Theory · Mathematics 2024-02-14 Aryeh Kontorovich , Amichai Painsky

Entropy is a measure of heterogeneity widely used in applied sciences, often when data are collected over space. Recently, a number of approaches has been proposed to include spatial information in entropy. The aim of entropy is to…

Statistics Theory · Mathematics 2019-11-12 Linda Altieri , Daniela Cocchi , Giulia Roli

Statistical models that include random effects are commonly used to analyze longitudinal and correlated data, often with strong and parametric assumptions about the random effects distribution. There is marked disagreement in the literature…

Methodology · Statistics 2012-01-11 Charles E. McCulloch , John M. Neuhaus

Many existing approaches for estimating parameters in settings with distributional shifts operate under an invariance assumption. For example, under covariate shift, it is assumed that $p(y|x)$ remains invariant. We refer to such…

Methodology · Statistics 2025-02-07 Yujin Jeong , Dominik Rothenhäusler

Knowing if a model will generalize to data 'in the wild' is crucial for safe deployment. To this end, we study model disagreement notions that consider the full predictive distribution - specifically disagreement based on Hellinger…

Machine Learning · Computer Science 2023-12-14 Mona Schirmer , Dan Zhang , Eric Nalisnick

Identifying and disentangling sources of predictive uncertainty is essential for trustworthy supervised learning. We argue that widely used second-order methods that disentangle aleatoric and epistemic uncertainty are fundamentally…

Machine Learning · Computer Science 2026-02-09 Sebastián Jiménez , Mira Jürgens , Willem Waegeman

Explicit finite-sample statistical guarantees on model performance are an important ingredient in responsible machine learning. Previous work has focused mainly on bounding either the expected loss of a predictor or the probability that an…

Machine Learning · Computer Science 2024-03-07 Zhun Deng , Thomas P. Zollo , Jake C. Snell , Toniann Pitassi , Richard Zemel

A decision must often be made between heavy-tailed and Gaussian errors for a regression or a time series model, and the t-distribution is frequently used when it is assumed that the errors are heavy-tailed distributed. The performance of…

Computation · Statistics 2015-05-11 J. Martin van Zyl

Determining the strength of non-linear statistical dependencies between two variables is a crucial matter in many research fields. The established measure for quantifying such relations is the mutual information. However, estimating mutual…

Data Analysis, Statistics and Probability · Physics 2019-07-24 Damián G. Hernández , Inés Samengo
‹ Prev 1 3 4 5 6 7 10 Next ›