English
Related papers

Related papers: Learning, complexity and information density

200 papers

We investigate a population of binary mistake sequences that result from learning with parametric models of different order. We obtain estimates of their error, algorithmic complexity and divergence from a purely random Bernoulli sequence.…

Artificial Intelligence · Computer Science 2010-10-14 Joel Ratsaby

Given a random binary sequence $X^{(n)}$ of random variables, $X_{t},$ $t=1,2,...,n$, for instance, one that is generated by a Markov source (teacher) of order $k^{*}$ (each state represented by $k^{*}$ bits). Assume that the probability of…

Machine Learning · Computer Science 2011-01-04 Joel Ratsaby

We review possible measures of complexity which might in particular be applicable to situations where the complexity seems to arise spontaneously. We point out that not all of them correspond to the intuitive (or "naive") notion, and that…

Data Analysis, Statistics and Probability · Physics 2012-08-20 Peter Grassberger

Since human randomness production has been studied and widely used to assess executive functions (especially inhibition), many measures have been suggested to assess the degree to which a sequence is random-like. However, each of them…

Computational Complexity · Computer Science 2013-12-10 Nicolas Gauvrit , Hector Zenil , Jean-Paul Delahaye , Fernando Soler-Toscano

Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random…

Machine Learning · Computer Science 2021-08-30 Christopher Sun , Jai Sharma , Milind Maiti

Evaluating the performance of classifiers is critical in machine learning, particularly in high-stakes applications where the reliability of predictions can significantly impact decision-making. Traditional performance measures, such as…

Machine Learning · Computer Science 2024-12-19 Jesus S. Aguilar-Ruiz

The randomness rate of an infinite binary sequence is characterized by the sequence of ratios between the Kolmogorov complexity and the length of the initial segments of the sequence. It is known that there is no uniform effective procedure…

Information Theory · Computer Science 2007-12-11 Marius Zimand

Complexity is a multi-faceted phenomenon, involving a variety of features including disorder, nonlinearity, and self-organisation. We use a recently developed rigorous framework for complexity to understand measures of complexity. We…

Adaptation and Self-Organizing Systems · Physics 2020-09-22 Karoline Wiesner , James Ladyman

A fundamental algorithm for selecting ranks from a finite subset of an ordered set is Radix Selection. This algorithm requires the data to be given as strings of symbols over an ordered alphabet, e.g., binary expansions of real numbers. Its…

Probability · Mathematics 2017-10-04 Kevin Leckey , Ralph Neininger , Henning Sulzbach

We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties of this sequence influence the error rates of continual…

Machine Learning · Computer Science 2019-08-06 Cuong V. Nguyen , Alessandro Achille , Michael Lam , Tal Hassner , Vijay Mahadevan , Stefano Soatto

We consider the sample complexity of learning with adversarial robustness. Most prior theoretical results for this problem have considered a setting where different classes in the data are close together or overlapping. Motivated by some…

Machine Learning · Computer Science 2023-01-19 Robi Bhattacharjee , Somesh Jha , Kamalika Chaudhuri

Stability is a central property in learning and statistics promising the output of an algorithm $A$ does not change substantially when applied to similar datasets $S$ and $S'$. It is an elementary fact that any sufficiently stable algorithm…

Machine Learning · Computer Science 2025-02-13 Max Hopkins , Shay Moran

Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this…

Machine Learning · Computer Science 2020-03-16 Marco Loog , Tom Viering , Alexander Mey

A supervised learning algorithm has access to a distribution of labeled examples, and needs to return a function (hypothesis) that correctly labels the examples. The hypothesis of the learner is taken from some fixed class of functions…

Machine Learning · Computer Science 2020-08-25 Eran Malach , Shai Shalev-Shwartz

The nature of concept learning is a core question in cognitive science. Theories must account for the relative difficulty of acquiring different concepts by supervised learners. For a canonical set of six category types, two distinct…

Information Theory · Computer Science 2015-03-03 Andreas D. Pape , Kenneth J. Kurtz , Hiroki Sayama

Correlation measure of order $k$ is an important measure of randomness in binary sequences. This measure tries to look for dependence between several shifted version of a sequence. We study the relation between the correlation measure of…

Information Theory · Computer Science 2021-07-27 Zhixiong Chen , Ana I. Gómez , Domingo Gómez-Pérez , Andrew Tirkel

This paper presents a novel information-theoretic perspective on generalization in machine learning by framing the learning problem within the context of lossy compression and applying finite blocklength analysis. In our approach, the…

Machine Learning · Computer Science 2026-02-05 Kosuke Sugiyama , Masato Uchida

Defect prediction is crucial for software quality assurance and has been extensively researched over recent decades. However, prior studies rarely focus on data complexity in defect prediction tasks, and even less on understanding the…

Software Engineering · Computer Science 2023-05-08 Xiaohui Wan , Zheng Zheng , Fangyun Qin , Xuhui Lu

Learning to hash is an efficient paradigm for exact and approximate nearest neighbor search from massive databases. Binary hash codes are typically extracted from an image by rounding output features from a CNN, which is trained on a…

Machine Learning · Computer Science 2020-05-12 Heikki Arponen , Tom E. Bishop

In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). We define memorization via the information a learning algorithm reveals about its training data…

Machine Learning · Computer Science 2024-07-19 Idan Attias , Gintare Karolina Dziugaite , Mahdi Haghifam , Roi Livni , Daniel M. Roy
‹ Prev 1 2 3 10 Next ›