English
Related papers

Related papers: Universality, optimality, and randomness deficienc…

200 papers

The classical likelihood ratio test (LRT) based on the asymptotic chi-squared distribution of the log likelihood is one of the fundamental tools of statistical inference. A recent universal LRT approach based on sample splitting provides…

Methodology · Statistics 2022-11-22 Robin Dunn , Aaditya Ramdas , Sivaraman Balakrishnan , Larry Wasserman

Universal methods for optimization are designed to achieve theoretically optimal convergence rates without any prior knowledge of the problem's regularity parameters or the accurarcy of the gradient oracle employed by the optimizer. In this…

Optimization and Control · Mathematics 2022-06-22 Kimon Antonakopoulos , Dong Quan Vu , Vokan Cevher , Kfir Y. Levy , Panayotis Mertikopoulos

The universal approximation theorem is generalised to uniform convergence on the (noncompact) input space $\mathbb{R}^n$. All continuous functions that vanish at infinity can be uniformly approximated by neural networks with one hidden…

Machine Learning · Computer Science 2024-03-05 Teun D. H. van Nuland

Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a…

Information Theory · Computer Science 2007-08-20 Marcus Hutter , Andrej Muchnik

We solve the problem of estimating the distribution of presumed i.i.d. observations for the total variation loss. Our approach is based on density models and is versatile enough to cope with many different ones, including some density…

Statistics Theory · Mathematics 2024-01-05 Y. Baraud , H. Halconruy , G. Maillard

In the Standard Model, lepton universality refers to the identical electroweak gauge interactions among charged leptons. The measurement of the branching ratio $R_{e / \mu} = \frac{\Gamma(\pi\rightarrow\ e…

High Energy Physics - Experiment · Physics 2013-08-27 Luca Doria

We discuss the possibility of performing precise tests of $\mu/e$ universality in $B \to\pi \ell^+\ell^-$ decays. We show that in wide regions of the dilepton invariant mass spectrum the ratio between muonic and electronic decay widths can…

High Energy Physics - Phenomenology · Physics 2021-10-13 Marzia Bordone , Claudia Cornella , Gino Isidori , Matthias König

Under a multinormal distribution with an arbitrary unknown covariance matrix, the main purpose of this paper is to propose a framework to achieve the goal of reconciliation of Bayesian, frequentist, and Fisher's reporting $p$-values,…

Statistics Theory · Mathematics 2024-12-10 Ming-Tien Tsai

We study algorithmic randomness properties for probability measures on Cantor space. We say that a measure $\mu$ on the space of infinite bit sequences is ML absolutely continuous if the non-ML-random bit sequences form a null set with…

Logic · Mathematics 2020-10-19 Andre Nies , Frank Stephan

Universal outlier hypothesis testing is studied in a sequential setting. Multiple observation sequences are collected, a small subset of which are outliers. A sequence is considered an outlier if the observations in that sequence are…

Statistics Theory · Mathematics 2014-11-27 Yun Li , Sirin Nitinawarat , Venugopal V. Veeravalli

We investigate the role of continuous reductions and continuous relativisation in the context of higher randomness. We define a higher analogue of Turing reducibility and show that it interacts well with higher randomness, for example with…

Logic · Mathematics 2015-03-18 Laurent Bienvenu , Noam Greenberg , Benoit Monin

In this paper we investigate algorithmic randomness on more general spaces than the Cantor space, namely computable metric spaces. To do this, we first develop a unified framework allowing computations with probability measures. We show…

Information Theory · Computer Science 2008-07-23 Mathieu Hoyrup , Cristobal Rojas

Universal hypothesis testing refers to the problem of deciding whether samples come from a nominal distribution or an unknown distribution that is different from the nominal distribution. Hoeffding's test, whose test statistic is equivalent…

Information Theory · Computer Science 2017-11-15 Pengfei Yang , Biao Chen

Solomonoff's central result on induction is that the posterior of a universal semimeasure M converges rapidly and with probability 1 to the true sequence generating posterior mu, if the latter is computable. Hence, M is eligible as a…

Machine Learning · Computer Science 2007-07-16 Marcus Hutter , Andrej Muchnik

Motivated by applications of biometric identification and content identification systems, we consider the problem of random coding for channels, where each codeword undergoes lossy compression (vector quantization), and where the decoder…

Information Theory · Computer Science 2016-09-29 Neri Merhav

Existing two-sample testing techniques, particularly those based on choosing a kernel for the Maximum Mean Discrepancy (MMD), often assume equal sample sizes from the two distributions. Applying these methods in practice can require…

Machine Learning · Statistics 2025-12-17 Aaron Wei , Milad Jalali , Danica J. Sutherland

Adversarial attacks against machine learning models are a rather hefty obstacle to our increasing reliance on these models. Due to this, provably robust (certified) machine learning models are a major topic of interest. Lipschitz continuous…

Machine Learning · Computer Science 2019-04-11 Jeremy E. J. Cohen , Todd Huster , Ra Cohen

We announce the extension of optimal regularity and Uhlenbeck compactness to the general setting of connections on vector bundles with non-compact gauge groups over non-Riemannian manifolds, including the Lorentzian metric connections of…

General Relativity and Quantum Cosmology · Physics 2023-03-29 Moritz Reintjes , Blake Temple

We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.~where each instantaneous loss is a scalar convex function of a linear function. We show…

Machine Learning · Computer Science 2022-11-01 Idan Amir , Roi Livni , Nathan Srebro

Convergence guarantees for optimization over bounded-rank matrices are delicate to obtain because the feasible set is a non-smooth and non-convex algebraic variety. Existing techniques include projected gradient descent, fixed-rank…

Optimization and Control · Mathematics 2024-06-21 Quentin Rebjock , Nicolas Boumal