English
Related papers

Related papers: A Large-Deviation Analysis of the Maximum-Likeliho…

200 papers

In Bayesian learning of Gaussian graphical model structure, it is common to restrict attention to certain classes of graphs and approximate the posterior distribution by repeatedly moving from one graph to another, using MCMC or methods…

Machine Learning · Statistics 2021-09-01 Edmund Jones

We present a new and surprisingly simple analysis of random-shift decompositions -- originally proposed by Miller, Peng, and Xu [SPAA'13]: We show that decompositions for exponentially growing scales $D = 2^0, 2^1, \ldots,…

Data Structures and Algorithms · Computer Science 2025-10-13 Rasmus Kyng , Maximilian Probst Gutenberg , Tim Rieder

This paper investigates a change-point estimation problem in the context of high-dimensional Markov Random Field models. Change-points represent a key feature in many dynamically evolving network structures. The change-point estimate is…

Methodology · Statistics 2018-02-13 Sandipan Roy , Yves Atchade , George Michailidis

Finding a minimum spanning tree (MST) for $n$ points in an arbitrary metric space is a fundamental primitive for hierarchical clustering and many other ML tasks, but this takes $\Omega(n^2)$ time to even approximate. We introduce a…

Data Structures and Algorithms · Computer Science 2025-02-19 Nate Veldt , Thomas Stanley , Benjamin W. Priest , Trevor Steil , Keita Iwabuchi , T. S. Jayram , Geoffrey Sanders

We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos. Dropout shifts the perfect-alignment fixed point, making the depth scale for information propagation finite even at critical…

Machine Learning · Computer Science 2026-05-22 Lucas Fernandez Sarmiento

The linear regression model with a random variable (RV) measurement matrix, where the mean of the random measurement matrix has full column rank, has been extensively studied. In particular, the quasiconvexity of the maximum likelihood…

Signal Processing · Electrical Eng. & Systems 2025-07-16 Ruohai Guo , Jiang Zhu , Xing Jiang , Fengzhong Qu

Modern reinforcement learning (RL) can be categorized into online and offline variants. As a pivotal aspect of both online and offline RL, current research on the Bellman equation revolves primarily around optimization techniques and…

Machine Learning · Computer Science 2023-12-14 Outongyi Lv , Bingxin Zhou

We propose a novel framework, called Markov-Lipschitz deep learning (MLDL), to tackle geometric deterioration caused by collapse, twisting, or crossing in vector-based neural network transformations for manifold-based representation…

Machine Learning · Computer Science 2020-10-01 Stan Z. Li , Zelin Zang , Lirong Wu

We develop optimal algorithms for learning undirected Gaussian trees and directed Gaussian polytrees from data. We consider both problems of distribution learning (i.e. in KL distance) and structure learning (i.e. exact recovery). The first…

Machine Learning · Computer Science 2024-02-12 Yuhao Wang , Ming Gao , Wai Ming Tai , Bryon Aragam , Arnab Bhattacharyya

We explore the application of computer vision and machine learning (ML) techniques to predict material properties (e.g. compressive strength) based on SEM images. We show that it's possible to train ML models to predict materials…

Given a finite typed rooted tree $T$ with $n$ vertices, the {\em empirical subtree measure} is the uniform measure on the $n$ typed subtrees of $T$ formed by taking all descendants of a single vertex. We prove a large deviation principle in…

Probability · Mathematics 2007-05-23 Amir Dembo , Peter Morters , Scott Sheffield

Consider a setting with $N$ independent individuals, each with an unknown parameter, $p_i \in [0, 1]$ drawn from some unknown distribution $P^\star$. After observing the outcomes of $t$ independent Bernoulli trials, i.e., $X_i \sim…

Statistics Theory · Mathematics 2019-02-13 Ramya Korlakai Vinayak , Weihao Kong , Gregory Valiant , Sham M. Kakade

We investigate statistical properties of a likelihood approach to nonparametric estimation of a singular distribution using deep generative models. More specifically, a deep generative model is used to model high-dimensional data that are…

Machine Learning · Statistics 2023-03-29 Minwoo Chae , Dongha Kim , Yongdai Kim , Lizhen Lin

Tree-based demappers for multiple-input multiple-output (MIMO) detection such as the sphere decoder can achieve near-optimal performance but incur high computational cost due to their sequential nature. In this paper, we propose the…

Information Theory · Computer Science 2022-09-12 Daniel E. Worrall , Markus Peschl , Arash Behboodi , Roberto Bondesan

We study the problem of approximating a discrete probability distribution, such as the next-token distribution of a large language model, by a dyadic distribution induced by a binary tree under encoding rate constraints. The objective is to…

Information Theory · Computer Science 2026-05-08 Daniella Bar-Lev , Farzad Farnoud , Ryan Gabrys

Generative Artificial Intelligence (GenAI) models, with their powerful feature learning capabilities, have been applied in many fields. In mobile wireless communications, GenAI can dynamically optimize the network to enhance the user…

Signal Processing · Electrical Eng. & Systems 2025-08-27 Changyuan Zhao , Jiacheng Wang , Ruichen Zhang , Dusit Niyato , Dong In Kim , Hongyang Du

In many real-world applications, from robotics to pedestrian trajectory prediction, there is a need to predict multiple real-valued outputs to represent several potential scenarios. Current deep learning techniques to address…

Machine Learning · Computer Science 2023-12-20 David D. Nguyen , David Liebowitz , Surya Nepal , Salil S. Kanhere

In this paper, we tackle for the first time the problem of maximum likelihood (ML) estimation of the signal-to-noise ratio (SNR) parameter over time-varying single-input multiple-output (SIMO) channels. Both the data-aided (DA) and the…

Applications · Statistics 2014-11-19 Faouzi Bellili , Rabii Meftehi , Sofiene Affes , Alex Stephenne

State-of-the-art Mixed Integer Linear Program (MILP) solvers combine systematic tree search with a plethora of hard-coded heuristics, such as the branching rule. The idea of learning branching rules from data has received increasing…

Machine Learning · Computer Science 2022-10-14 Lara Scavuzzo , Feng Yang Chen , Didier Chételat , Maxime Gasse , Andrea Lodi , Neil Yorke-Smith , Karen Aardal

Machine learning (ML) has emerged as a powerful tool for tackling complex regression and classification tasks, yet its success often hinges on the quality of training data. This study introduces an ML paradigm inspired by domain knowledge…

Machine Learning · Computer Science 2025-01-10 Mohsen Rashki