中文
相关论文

相关论文: The Information Complexity of Learning Tasks, thei…

200 篇论文

The task of modelling and forecasting a dynamical system is one of the oldest problems, and it remains challenging. Broadly, this task has two subtasks - extracting the full dynamical information from a partial observation; and then…

动力系统 · 数学 2022-08-16 Tyrus Berry , Suddhasattwa Das

Graph comparison plays a major role in many network applications. We often need a similarity metric for comparing networks according to their structural properties. Various network features - such as degree distribution and clustering…

社会与信息网络 · 计算机科学 2013-07-16 Sadegh Aliakbary , Sadegh Motallebi , Jafar Habibi , Ali Movaghar

Generalization is a central aspect of learning theory. Here, we propose a framework that explores an auxiliary task-dependent notion of generalization, and attempts to quantitatively answer the following question: given two sets of patterns…

无序系统与神经网络 · 物理学 2020-01-08 Francesco Borra , Marco Cosentino Lagomarsino , Pietro Rotondo , Marco Gherardi

We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions…

机器学习 · 计算机科学 2023-03-15 Grzegorz Głuch , Rudiger Urbanke

This is the first of a series of papers in which we study deep computations (ultracomputations) and deep iterates, formalizing the ideas of "asymptotic limit" of computations and compositional iterates, respectively. In this first paper of…

逻辑 · 数学 2026-01-28 Samson Alva , Eduardo Dueñez , Jose Iovino , Claire Walton

The inverse statistical problem of finding direct interactions in complex networks is difficult. In the natural sciences, well-controlled perturbation experiments are widely used to probe the structure of complex networks. However, our…

无序系统与神经网络 · 物理学 2019-10-24 Jialong Jiang , David A. Sivak , Matt Thomson

Integrating knowledge across different domains is an essential feature of human learning. Learning paradigms such as transfer learning, meta-learning, and multi-task learning reflect the human learning process by exploiting the prior…

机器学习 · 计算机科学 2024-10-17 Richa Upadhyay , Ronald Phlypo , Rajkumar Saini , Marcus Liwicki

We present ComplexityNet, a streamlined language model designed for assessing task complexity. This model predicts the likelihood of accurate output by various language models, each with different capabilities. Our initial application of…

计算与语言 · 计算机科学 2024-10-16 Henry Bae , Aghyad Deeb , Alex Fleury , Kehang Zhu

It is not obvious what fraction of all the potential information residing in the molecules and structures of living systems is significant or meaningful to the system. Sets of random sequences or identically repeated sequences, for example,…

信息论 · 计算机科学 2008-01-28 David J. Galas , Matti Nykter , Gregory W. Carter , Nathan D. Price , Ilya Shmulevich

The normalized information distance is a universal distance measure for objects of all kinds. It is based on Kolmogorov complexity and thus uncomputable, but there are ways to utilize it. First, compression algorithms can be used to…

信息检索 · 计算机科学 2008-09-16 Paul M. B. Vitanyi , Frank J. Balbach , Rudi L. Cilibrasi , Ming Li

We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Unlike existing multi-task learning methodologies, the graph structure is not assumed…

机器学习 · 计算机科学 2020-09-15 Shujian Yu , Francesco Alesiani , Ammar Shaker , Wenzhe Yin

Model complexity is a fundamental problem in deep learning. In this paper we conduct a systematic overview of the latest studies on model complexity in deep learning. Model complexity of deep learning can be categorized into expressive…

机器学习 · 计算机科学 2021-08-04 Xia Hu , Lingyang Chu , Jian Pei , Weiqing Liu , Jiang Bian

One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. The theory of meta-learning is still in its early stages,…

机器学习 · 计算机科学 2020-02-27 Nikunj Saunshi , Yi Zhang , Mikhail Khodak , Sanjeev Arora

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and…

机器学习 · 计算机科学 2026-05-21 Divij Khaitan , Subhashis Banerjee

While humans and animals learn incrementally during their lifetimes and exploit their experience to solve new tasks, standard deep reinforcement learning methods specialize to solve only one task at a time. As a result, the information they…

人工智能 · 计算机科学 2022-02-23 Diego Gomez , Nicanor Quijano , Luis Felipe Giraldo

While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided…

机器学习 · 统计学 2019-06-13 Xu He , Jakub Sygnowski , Alexandre Galashov , Andrei A. Rusu , Yee Whye Teh , Razvan Pascanu

Meta-learning aims at optimizing the hyperparameters of a model class or training algorithm from the observation of data from a number of related tasks. Following the setting of Baxter [1], the tasks are assumed to belong to the same task…

机器学习 · 计算机科学 2021-05-11 Sharu Theresa Jose , Osvaldo Simeone

Many tasks in graphics and vision demand machinery for converting shapes into consistent representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage. When the source data is noisy or…

图形学 · 计算机科学 2021-11-24 Dmitriy Smirnov , Matthew Fisher , Vladimir G. Kim , Richard Zhang , Justin Solomon

A general notion of information-related complexity applicable to both natural and man-made systems is proposed. The overall approach is to explicitly consider a rational agent performing a certain task with a quantifiable degree of success.…

数据分析、统计与概率 · 物理学 2013-01-18 Eugene Perevalov , David Grace

Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation…

人工智能 · 计算机科学 2026-04-28 Nikolaos Al. Papadopoulos , Konstantinos E. Psannis