English
Related papers

Related papers: Minimax Bounds for Distributed Logistic Regression

200 papers

In this paper, we consider a least-squares (LS)-based distributed algorithm build on a sensor network to estimate an unknown parameter vector of a dynamical system, where each sensor in the network has partial information only but is…

Systems and Control · Electrical Eng. & Systems 2022-12-19 Siyu Xie , Yaqi Zhang , Lei Guo

We consider the fundamental problem of estimating a discrete distribution on a domain of size $K$ with high probability in Kullback-Leibler divergence. We provide upper and lower bounds on the minimax estimation rate, which show that the…

Machine Learning · Statistics 2026-02-23 Dirk van der Hoeven , Julia Olkhovskaia , Tim van Erven

Data shuffling between distributed cluster of nodes is one of the critical steps in implementing large-scale learning algorithms. Randomly shuffling the data-set among a cluster of workers allows different nodes to obtain fresh data…

Information Theory · Computer Science 2018-01-08 Mohamed A. Attia , Ravi Tandon

We propose two families of asymptotically local minimax lower bounds on parameter estimation performance. The first family of bounds applies to any convex, symmetric loss function that depends solely on the difference between the estimate…

Statistics Theory · Mathematics 2024-09-20 Neri Merhav

We study the problem of finding the best linear model that can minimize least-squares loss given a data-set. While this problem is trivial in the low dimensional regime, it becomes more interesting in high dimensions where the population…

Machine Learning · Computer Science 2021-02-09 Yahya Sattar , Samet Oymak

We consider a MapReduce-like distributed computing system. We derive a lower bound on the communication cost for any given storage and computation costs. This lower bound matches the achievable bound we proposed recently. As a result, we…

Information Theory · Computer Science 2020-01-23 Qifa Yan , Sheng Yang , Michèle Wigger

One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic…

Machine Learning · Statistics 2026-03-24 Avrajit Ghosh , Bin Yu , Manfred Warmuth , Peter Bartlett

This paper proposes a new family of lower and upper bounds on the minimum mean squared error (MMSE). The key idea is to minimize/maximize the MMSE subject to the constraint that the joint distribution of the input-output statistics lies in…

Information Theory · Computer Science 2020-06-09 Michael Fauß , Alex Dysto , H. Vincent Poor

The problem of determining the achievable sensitivity with digitization exhibiting minimal complexity is addressed. In this case, measurements are exclusively available in hard-limited form. Assessing the achievable sensitivity via the…

Information Theory · Computer Science 2021-06-11 Manuel S. Stein

Distribution data refers to a data set where each sample is represented as a probability distribution, a subject area receiving burgeoning interest in the field of statistics. Although several studies have developed…

Methodology · Statistics 2024-02-09 Ryo Okano , Masaaki Imaizumi

This paper presents a randomized Las Vegas distributed algorithm that constructs a minimum spanning tree (MST) in weighted networks with optimal (up to polylogarithmic factors) time and message complexity. This algorithm runs in…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-01-25 Gopal Pandurangan , Peter Robinson , Michele Scquizzato

We consider distributed statistical optimization in one-shot setting, where there are $m$ machines each observing $n$ i.i.d. samples. Based on its observed samples, each machine then sends an $O(\log(mn))$-length message to a server, at…

Machine Learning · Computer Science 2019-11-12 Arsalan Sharifnassab , Saber Salehkaleybar , S. Jamaloddin Golestani

Let $(X_i)_{1 \le i \le n}$ be independent and identically distributed (i.i.d.) standard Gaussian random variables, and denote by $X_{(n)} = \max_{1 \le i \le n} X_i$ the maximum order statistic. It is well-known in extreme value theory…

Probability · Mathematics 2025-07-15 Yutao Ma , Bingjie Tian

The prior independent framework for algorithm design considers how well an algorithm that does not know the distribution of its inputs approximates the expected performance of the optimal algorithm for this distribution. This paper gives a…

Computer Science and Game Theory · Computer Science 2021-07-13 Jason Hartline , Aleck Johnsen

Missing data is a crucial issue when applying machine learning algorithms to real-world datasets. Starting from the simple assumption that two batches extracted randomly from the same dataset should share the same distribution, we leverage…

Machine Learning · Statistics 2020-07-02 Boris Muzellec , Julie Josse , Claire Boyer , Marco Cuturi

We present a framework for the theoretical analysis of ensembles of low-complexity empirical risk minimisers trained on independent random compressions of high-dimensional data. First we introduce a general distribution-dependent…

Machine Learning · Computer Science 2021-06-03 Henry W. J. Reeve , Ata Kaban

We consider the estimation problem in high-dimensional semi-supervised learning. Our goal is to investigate when and how the unlabeled data can be exploited to improve the estimation of the regression parameters of linear model in light of…

Methodology · Statistics 2023-03-21 Siyi Deng , Yang Ning , Jiwei Zhao , Heping Zhang

Many causal and structural parameters in economics can be identified and estimated by computing the value of an optimization program over all distributions consistent with the model and the data. Existing tools apply when the data is…

Econometrics · Economics 2025-07-31 Andrei Voronin

The principle of minimum Fisher information states that in the set of acceptable probability distributions characterizing the given system, it is best done by the one that minimizes the corresponding Fisher information. This principle can…

General Finance · Quantitative Finance 2022-03-24 Marcin Makowski , Edward W. Piotrowski , Piotr Frąckiewicz , Marek Szopa

For a regression problem with a binary label response, we examine the problem of constructing confidence intervals for the label probability conditional on the features. In a setting where we do not have any information about the underlying…

Statistics Theory · Mathematics 2020-10-09 Rina Foygel Barber