English
Related papers

Related papers: Data processing inequalities based on a certain st…

200 papers

Recently, there is a growing interest in the study of median-based algorithms for distributed non-convex optimization. Two prominent such algorithms include signSGD with majority vote, an effective approach for communication reduction via…

Machine Learning · Computer Science 2019-06-07 Xiangyi Chen , Tiancong Chen , Haoran Sun , Zhiwei Steven Wu , Mingyi Hong

Understanding geometric properties of natural language processing models' latent spaces allows the manipulation of these properties for improved performance on downstream tasks. One such property is the amount of data spread in a model's…

Machine Learning · Computer Science 2023-08-02 Anna C. Marbut , Katy McKinney-Bock , Travis J. Wheeler

This paper focuses on a specific aspect of human visual discrimination from computationally generated solutions for CAAD ends. The bottleneck at work here concern informational ratios of discriminative rates over generative ones. The amount…

Human-Computer Interaction · Computer Science 2024-12-30 Pierre Cutellic

Inequalities between transportation costs and Fisher information are known to characterize certain concentration properties of Markov processes around their invariant measures. This note provides a new characterization of the quadratic…

Probability · Mathematics 2020-12-07 Daniel Lacker , Lane Chun Yeung

The use of correntropy as a similarity measure has been increasing in different scenarios due to the well-known ability to extract high-order statistic information from data. Recently, a new similarity measure between complex random…

Information Theory · Computer Science 2017-10-03 João Guimarães

Efficient information processing is crucial for both living organisms and engineered systems. The mutual information rate, a core concept of information theory, quantifies the amount of information shared between the trajectories of input…

Molecular Networks · Quantitative Biology 2025-09-01 Manuel Reinhardt , Age J. Tjalma , Anne-Lena Moor , Christoph Zechner , Pieter Rein ten Wolde

We derive bounds for the Orlicz norm of the deviation of a random variable defined on $\mathbb{R}^n$ from its Gaussian mean value. The random variables are assumed to be smooth and the bound itself depends on the Orlicz norm of the…

Statistics Theory · Mathematics 2021-01-11 Giovanni Pistone

In this paper, we consider single- and multi-user Gaussian channels with feedback under expected power constraints and with non-vanishing error probabilities. In the first of two contributions, we study asymptotic expansions for the…

Information Theory · Computer Science 2016-09-22 Lan V. Truong , Silas L. Fong , Vincent Y. F. Tan

We prove new probabilistic upper bounds on generalization error of complex classifiers that are combinations of simple classifiers. Such combinations could be implemented by neural networks or by voting methods of combining the classifiers,…

Probability · Mathematics 2007-05-23 Vladimir Koltchinskii , Dmitry Panchenko

Many network analysis and graph learning techniques are based on models of random walks which require to infer transition matrices that formalize the underlying stochastic process in an observed graph. For weighted graphs, it is common to…

Methodology · Statistics 2022-10-28 Vincenzo Perri , Luka V. Petrović , Ingo Scholtes

With continuous outcomes, the average causal effect is typically defined using a contrast of expected potential outcomes. However, in the presence of skewed outcome data, the expectation may no longer be meaningful. In practice the typical…

Methodology · Statistics 2023-02-06 Daisy A. Shepherd , Benjamin R. Baer , Margarita Moreno-Betancur

Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes. Contemporary studies on DNN imply that such sample difference is rooted on the distribution of intrinsic pattern…

Machine Learning · Computer Science 2021-08-19 Chi Zhang , Xiaoning Ma , Yu Liu , Le Wang , Yuanqi Su , Yuehu Liu

Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Mauricio Delbracio , Hossein Talebi , Peyman Milanfar

Many real-world problems in machine learning, signal processing, and communications assume that an unknown vector $x$ is measured by a matrix A, resulting in a vector $y=Ax+z$, where $z$ denotes the noise; we call this a single measurement…

Information Theory · Computer Science 2017-07-13 Junan Zhu

This paper studies statistical aggregation procedures in regression setting. A motivating factor is the existence of many different methods of estimation, leading to possibly competing estimators. We consider here three different types of…

Statistics Theory · Mathematics 2007-06-13 Florentina Bunea , Alexandre Tsybakov , Marten Wegkamp

Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have provided insights to understanding the generalizability in…

Machine Learning · Computer Science 2020-05-12 Jingling Li , Yanchao Sun , Jiahao Su , Taiji Suzuki , Furong Huang

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found two blind spots in…

Machine Learning · Computer Science 2021-10-26 Zhongzhan Huang , Wenqi Shao , Xinjiang Wang , Liang Lin , Ping Luo

We introduce constrained Gaussian process (CGP), a Gaussian process model for random functions that allows easy placement of mathematical constrains (e.g., non-negativity, monotonicity, etc) on its sample functions. CGP comes with…

Statistics Theory · Mathematics 2019-04-23 Jeremiah Zhe Liu

Upper and lower bounds are obtained for the joint entropy of a collection of random variables in terms of an arbitrary collection of subset joint entropies. These inequalities generalize Shannon's chain rule for entropy as well as…

Information Theory · Computer Science 2024-05-07 Mokshay Madiman , Prasad Tetali

As shown in recent research, deep neural networks can perfectly fit randomly labeled data, but with very poor accuracy on held out data. This phenomenon indicates that loss functions such as cross-entropy are not a reliable indicator of…

Machine Learning · Statistics 2019-06-13 Yiding Jiang , Dilip Krishnan , Hossein Mobahi , Samy Bengio