中文
相关论文

相关论文: Rules of Thumb for Information Acquisition from La…

200 篇论文

We study empirical scaling laws for transfer learning between distributions in an unsupervised, fine-tuning setting. When we train increasingly large neural networks from-scratch on a fixed-size dataset, they eventually become data-limited…

机器学习 · 计算机科学 2021-02-03 Danny Hernandez , Jared Kaplan , Tom Henighan , Sam McCandlish

We study a novel model for evolution of complex networks. We introduce information filtering for reduction of the number of available nodes to a randomly chosen sample, as stochastic component of evolution. New nodes are attached to the…

无序系统与神经网络 · 物理学 2009-11-10 H. Stefancic , V. Zlatic

Organisms and algorithms learn probability distributions from previous observations, either over evolutionary time or on the fly. In the absence of regularities, estimating the underlying distribution from data would require observing each…

统计力学 · 物理学 2024-12-10 William Bialek , Stephanie E. Palmer , David J. Schwab

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the…

信息论 · 计算机科学 2026-02-03 Kenneth Bogert , Matthew Kothe

Information spread in social media depends on a number of factors, including how the site displays information, how users navigate it to find items of interest, users' tastes, and the `virality' of information, i.e., its propensity to be…

社会与信息网络 · 计算机科学 2015-02-03 Jeon-Hyung Kang , Kristina Lermam

Given i.i.d.~samples from an unknown distribution $P$, the goal of distribution learning is to recover the parameters of a distribution that is close to $P$. When $P$ belongs to the class of product distributions on the Boolean hypercube…

机器学习 · 计算机科学 2025-11-14 Arnab Bhattacharyya , Davin Choo , Philips George John , Themis Gouleakis

The statistical state for the empirical Pareto's 80/20 rule has been found to correspond to a normal or Gaussian distribution with a standard deviation that is twice the mean. This finding represents large characteristic variations in our…

综合金融 · 定量金融 2020-10-01 Katsuaki Tanabe

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

机器学习 · 计算机科学 2021-05-20 Kanika Madan , Nan Rosemary Ke , Anirudh Goyal , Bernhard Schölkopf , Yoshua Bengio

Partial information decomposition (PID) of the multivariate mutual information describes the distinct ways in which a set of source variables contains information about a target variable. The groundbreaking work of Williams and Beer has…

信息论 · 计算机科学 2021-03-31 Abdullah Makkeh , Aaron J. Gutknecht , Michael Wibral

For many interesting tasks, such as medical diagnosis and web page classification, a learner only has access to some positively labeled examples and many unlabeled examples. Learning from this type of data requires making assumptions about…

机器学习 · 计算机科学 2018-08-28 Jessa Bekker , Jesse Davis

In this paper, we seek to measure how much information a component in a neural network could extract from the representations fed into it. Our work stands in contrast to prior probing work, most of which investigates how much information a…

计算与语言 · 计算机科学 2022-11-14 Tiago Pimentel , Josef Valvoda , Niklas Stoehr , Ryan Cotterell

The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed data for training. Incomplete data is a common issue in…

机器学习 · 计算机科学 2023-07-04 Yidong Ouyang , Liyan Xie , Chongxuan Li , Guang Cheng

Classification rules can be severely affected by the presence of disturbing observations in the training sample. Looking for an optimal classifier with such data may lead to unnecessarily complex rules. So, simpler effective classification…

统计理论 · 数学 2017-01-19 Marina Antolín , Eustasio Del Barrio , Jean-Michel Loubes

Relational inference leverages relationships between entities and links in a network to infer information about the network from a small sample. This method is often used when global information about the network is not available or…

社会与信息网络 · 计算机科学 2018-03-08 Lisette Espín-Noboa , Claudia Wagner , Fariba Karimi , Kristina Lerman

Data-driven risk analysis involves the inference of probability distributions from measured or simulated data. In the case of a highly reliable system, such as the electricity grid, the amount of relevant data is often exceedingly limited,…

统计方法学 · 统计学 2017-07-11 Simon H. Tindemans , Goran Strbac

Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available…

机器学习 · 计算机科学 2017-11-15 Eleni Triantafillou , Richard Zemel , Raquel Urtasun

The aim of this work is to provide bounds connecting two probability measures of the same event using R\'enyi $\alpha$-Divergences and Sibson's $\alpha$-Mutual Information, a generalization of respectively the Kullback-Leibler Divergence…

信息论 · 计算机科学 2020-01-20 Amedeo Roberto Esposito , Michael Gastpar , Ibrahim Issa

Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must…

人工智能 · 计算机科学 2008-06-26 Marco Zaffalon , Marcus Hutter

Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address questions such as the reliability of the empirical value, one must…

人工智能 · 计算机科学 2014-08-08 Marco Zaffalon , Marcus Hutter

We consider the problem of decision-making with side information and unbounded loss functions. Inspired by probably approximately correct learning model, we use a slightly different model that incorporates the notion of side information in…

机器学习 · 计算机科学 2007-07-13 Majid Fozunbal , Ton Kalker