English
Related papers

Related papers: $L_q$ Lower Bounds on Distributed Estimation via F…

200 papers

This paper establishes the equivalence between Local Differential Privacy (LDP) and a global limit on learning any knowledge specific to a queried object. However, an output from an LDP query is not necessarily required to provide exact…

Cryptography and Security · Computer Science 2025-05-01 Mingen Pan

Results by van der Vaart (1991) from semi-parametric statistics about the existence of a non-zero Fisher information are reviewed in an infinite-dimensional non-linear Gaussian regression setting. Information-theoretically optimal inference…

Statistics Theory · Mathematics 2021-07-21 Richard Nickl , Gabriel Paternain

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

We study the sequential general online regression, known also as the sequential probability assignments, under logarithmic loss when compared against a broad class of experts. We focus on obtaining tight, often matching, lower and upper…

Machine Learning · Computer Science 2023-02-02 Changlong Wu , Mohsen Heidari , Ananth Grama , Wojciech Szpankowski

The Fisher information matrix (FIM) has long been of interest in statistics and other areas. It is widely used to measure the amount of information and calculate the lower bound for the variance for maximum likelihood estimation (MLE). In…

Information Theory · Computer Science 2015-06-19 Shenghan Guo

This paper is on developing some computer-assisted proof methods involving non-classical inequalities for Shannon entropy. Two areas of the applications of information inequalities are studied: Secret sharing schemes and hat guessing games.…

Information Theory · Computer Science 2023-10-19 Emirhan Gürpınar

Recent research has used margin theory to analyze the generalization performance for deep neural networks (DNNs). The existed results are almost based on the spectrally-normalized minimum margin. However, optimizing the minimum margin…

Machine Learning · Computer Science 2024-07-10 Shen-Huan Lyu , Lu Wang , Zhi-Hua Zhou

Quantum Cram\'er--Rao theory is intrinsically local: it bounds precision near a specified parameter value, and its saturating measurement generally depends on that value. Barankin-type bounds use finite parameter displacements, but remain…

Quantum Physics · Physics 2026-05-28 Hai-Long Shi , Augusto Smerzi

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression under L^\infty constraints on the linear combination. When the input distribution is known, there already exists…

Statistics Theory · Mathematics 2011-09-14 Jean-Yves Audibert , Olivier Catoni

Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively. However, to obtain bounds, current techniques use strict assumptions such as a uniformly bounded or a Lipschitz…

Machine Learning · Computer Science 2020-02-25 Yossi Adi , Yaniv Nemcovsky , Alex Schwing , Tamir Hazan

This paper presents a distributed estimator for a deterministic parametric physical field sensed by a homogeneous sensor network and develops a new transformed expression for the Cramer-Rao lower bound (CRLB) on the variance of distributed…

Information Theory · Computer Science 2015-06-17 Salvatore Talarico , Natalia A. Schmid , Marwan Alkhweldi , Matthew C. Valenti

Lower bounds involving $f$-divergences between the underlying probability measures are proved for the minimax risk in estimation problems. Our proofs just use simple convexity facts. Special cases and straightforward corollaries of our…

Statistics Theory · Mathematics 2011-02-22 Adityanand Guntuboyina

We consider the problem of training a classification model with group annotated training data. Recent work has established that, if there is distribution shift across different groups, models trained using the standard empirical risk…

Machine Learning · Computer Science 2022-04-21 Vihari Piratla , Praneeth Netrapalli , Sunita Sarawagi

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

The problem of determining the intrinsic quality of a signal processing system with respect to the inference of an unknown deterministic parameter $\theta$ is considered. While the Fisher information measure $F(\theta)$ forms a classical…

Information Theory · Computer Science 2018-05-30 Manuel Stein , Josef A. Nossek

We identify fundamental tradeoffs between statistical utility and privacy under local models of privacy in which data is kept private even from the statistician, providing instance-specific bounds for private estimation and learning…

Statistics Theory · Mathematics 2020-10-01 John C. Duchi , Feng Ruan

We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks. In particular, MFVI fails to give…

Machine Learning · Statistics 2019-06-28 Andrew Y. K. Foong , Yingzhen Li , José Miguel Hernández-Lobato , Richard E. Turner

This paper considers the problem of matrix-variate logistic regression. It derives the fundamental error threshold on estimating low-rank coefficient matrices in the logistic regression problem by obtaining a lower bound on the minimax…

Machine Learning · Computer Science 2022-05-10 Batoul Taki , Mohsen Ghassemi , Anand D. Sarwate , Waheed U. Bajwa

We present a novel prior for tree topology within Bayesian Additive Regression Trees (BART) models. This approach quantifies the hypothetical loss in information and the loss due to complexity associated with choosing the wrong tree…

Methodology · Statistics 2024-12-30 F. Serafini , F. Leisen , C. Villa , K. Wilson

The most effective differentially private machine learning algorithms in practice rely on an additional source of purportedly public data. This paradigm is most interesting when the two sources combine to be more than the sum of their…

Machine Learning · Computer Science 2025-07-25 Amrith Setlur , Pratiksha Thaker , Jonathan Ullman