English
Related papers

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

200 papers

This paper proposes an original Riemmanian geometry for low-rank structured elliptical models, i.e., when samples are elliptically distributed with a covariance matrix that has a low-rank plus identity structure. The considered geometry is…

Differential Geometry · Mathematics 2020-01-07 Florent Bouchard , Arnaud Breloy , Guillaume Ginolhac , Alexandre Renaux , Frédéric Pascal

In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables. These…

Machine Learning · Statistics 2018-09-27 Huangjie Zheng , Jiangchao Yao , Ya Zhang , Ivor W. Tsang , Jia Wang

Statistical divergences are important tools in data analysis, information theory, and statistical physics, and there exist well known inequalities on their bounds. However, in many circumstances involving temporal evolution, one needs…

Data Analysis, Statistics and Probability · Physics 2025-03-25 Jan Karbowski

We address differential privacy for fully distributed optimization subject to a shared inequality constraint. By co-designing the distributed optimization mechanism and the differential-privacy noise injection mechanism, we propose the…

Optimization and Control · Mathematics 2024-04-04 Yongqiang Wang , Angelia Nedic

Empirical Risk Minimization (ERM) algorithms are widely used in a variety of estimation and prediction tasks in signal-processing and machine learning applications. Despite their popularity, a theory that explains their statistical…

Machine Learning · Statistics 2020-07-07 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis

In this paper we study the differentially private Empirical Risk Minimization (ERM) problem in different settings. For smooth (strongly) convex loss function with or without (non)-smooth regularization, we give algorithms that achieve…

Machine Learning · Computer Science 2018-02-15 Di Wang , Minwei Ye , Jinhui Xu

Bayesian inference typically requires the computation of an approximation to the posterior distribution. An important requirement for an approximate Bayesian inference algorithm is to output high-accuracy posterior mean and uncertainty…

Statistics Theory · Mathematics 2018-10-03 Jonathan H. Huggins , Trevor Campbell , Mikołaj Kasprzak , Tamara Broderick

We prove that two well-known measures of information are interrelated in interesting and useful ways when applied to nonequilibrium circumstances. A nontrivial form of the lower bound for the Fisher information measure is derived in…

Statistical Mechanics · Physics 2012-04-06 Takuya Yamano

The trace $\tr(q(\ma{L} + q\ma{I})^{-1})$, where $\ma{L}$ is a symmetric diagonally dominant matrix, is the quantity of interest in some machine learning problems. However, its direct computation is impractical if the matrix size is large.…

Signal Processing · Electrical Eng. & Systems 2022-09-14 Yusuf Yigit Pilavci , Pierre-Olivier Amblard , Simon Barthelme , Nicolas Tremblay

Linear Least Squares is a very well known technique for parameter estimation, which is used even when sub-optimal, because of its very low computational requirements and the fact that exact knowledge of the noise statistics is not required.…

Signal Processing · Electrical Eng. & Systems 2017-11-01 Michael Krikheli , Amir Leshem

We prove new lower bounds for statistical estimation tasks under the constraint of $(\varepsilon, \delta)$-differential privacy. First, we provide tight lower bounds for private covariance estimation of Gaussian distributions. We show that…

Data Structures and Algorithms · Computer Science 2023-03-29 Gautam Kamath , Argyris Mouzakis , Vikrant Singhal

Gaussian latent tree models, or more generally, Gaussian latent forest models have Fisher-information matrices that become singular along interesting submodels, namely, models that correspond to subforests. For these singularities, we…

Methodology · Statistics 2015-12-24 Mathias Drton , Shaowei Lin , Luca Weihs , Piotr Zwiernik

We devise a systematic method to determine the Fisher information required for resolving two incoherent point sources with a diffraction-limited linear imaging device. The resulting Cram\'er-Rao bound gives the lowest variance achievable…

Quantum Physics · Physics 2016-07-21 J. Rehacek , M. Paur , B. Stoklasa , L. Motka , Z. Hradil , L. L. Sanchez-Soto

Many psychological theories can be operationalized as linear inequality constraints on the parameters of multinomial distributions (e.g., discrete choice analysis). These constraints can be described in two equivalent ways: Either as the…

Computation · Statistics 2019-04-23 Daniel W. Heck , Clintin P. Davis-Stober

This review aims at gathering the most relevant quantum multi-parameter estimation methods that go beyond the direct use of the Quantum Fisher Information concept. We discuss in detail the Holevo Cram\'er-Rao bound, the Quantum Local…

Quantum Physics · Physics 2020-09-02 Rafal Demkowicz-Dobrzanski , Wojciech Gorecki , Madalin Guta

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 2022-11-03 Itai Gat , Yossi Adi , Alexander Schwing , Tamir Hazan

We study distributed estimation methods under communication constraints in a distributed version of the nonparametric random design regression model. We derive minimax lower bounds and exhibit methods that attain those bounds. Moreover, we…

Statistics Theory · Mathematics 2019-02-06 Botond Szabo , Harry van Zanten

We develop and analyze methods for computing provably optimal {\em maximum a posteriori} (MAP) configurations for a subclass of Markov random fields defined on graphs with cycles. By decomposing the original distribution into a convex…

Information Theory · Computer Science 2007-07-13 Martin J. Wainwright , Tommi S. Jaakkola , Alan S. Willsky

We consider a standard distributed optimisation setting where $N$ machines, each holding a $d$-dimensional function $f_i$, aim to jointly minimise the sum of the functions $\sum_{i = 1}^N f_i (x)$. This problem arises naturally in…

Machine Learning · Computer Science 2021-12-08 Dan Alistarh , Janne H. Korhonen

Invariant Causal Prediction (Peters et al., 2016) is a technique for out-of-distribution generalization which assumes that some aspects of the data distribution vary across the training set but that the underlying causal mechanisms remain…

Machine Learning · Computer Science 2021-03-30 Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski
‹ Prev 1 8 9 10 Next ›