English
Related papers

Related papers: Generalized Compression Dictionary Distance as Uni…

200 papers

We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an…

Machine Learning · Computer Science 2019-05-21 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

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

We study a generalization of deduplication, which enables lossless deduplication of highly similar data and show that standard deduplication with fixed chunk length is a special case. We provide bounds on the expected length of coded…

Information Theory · Computer Science 2020-03-04 Rasmus Vestergaard , Qi Zhang , Daniel E. Lucani

In scientific simulations, observations, and experiments, the cost of transferring data to and from disk and across networks has become a significant bottleneck that particularly impacts subsequent data analysis and visualization. To…

Databases · Computer Science 2023-08-24 Victor A. P. Magri , Peter Lindstrom

The ability to discriminate similar visual stimuli is an important index of memory function. This ability is widely thought to be supported by expanding the dimensionality of relevant neural codes, such that neural representations for…

Neurons and Cognition · Quantitative Biology 2025-10-14 Dale Zhou , Sharon Mina Noh , Nora C Harhen , Nidhi V Banavar , C. Brock Kirwan , Michael A Yassa , Aaron M Bornstein

Dependency distance minimization (DDm) is a well-established principle of word order. It has been predicted theoretically that DDm implies compression, namely the minimization of word lengths. This is a second order prediction because it…

Computation and Language · Computer Science 2023-10-16 Ramon Ferrer-i-Cancho , Carlos Gómez-Rodríguez

We focus on the task of unsupervised lemmatization, i.e. grouping together inflected forms of one word under one label (a lemma) without the use of annotated training data. We propose to perform agglomerative clustering of word forms with a…

Computation and Language · Computer Science 2019-08-23 Rudolf Rosa , Zdeněk Žabokrtský

Understanding and developing a correlation measure that can detect general dependencies is not only imperative to statistics and machine learning, but also crucial to general scientific discovery in the big data age. In this paper, we…

Machine Learning · Statistics 2024-06-27 Cencheng Shen , Carey E. Priebe , Joshua T. Vogelstein

One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the Internet explosion and the massive diffusion of…

Artificial Intelligence · Computer Science 2017-01-12 Valentina Franzoni

Clustering algorithms have long been the topic of research, representing the more popular side of unsupervised learning. Since clustering analysis is one of the best ways to find some clarity and structure within raw data, this paper…

Machine Learning · Computer Science 2025-11-25 Naitik Gada

Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), which predict that simpler models generalize better when data arises from low-complexity…

Machine Learning · Computer Science 2026-05-14 Lukas Silvester Barth , Paulo von Petersenn

Over the last few years, machine learning unlocked previously infeasible features for compression, such as providing guarantees for users' privacy or tailoring compression to specific data statistics (e.g., satellite images or audio…

Information Theory · Computer Science 2026-03-25 Gergely Flamich

We present a smooth probabilistic reformulation of $\ell_0$ regularized regression that does not require Monte Carlo sampling and allows for the computation of exact gradients, facilitating rapid convergence to local optima of the best…

Machine Learning · Computer Science 2025-09-19 Lukas Silvester Barth , Paulo von Petersenn

Normalized web distance (NWD) is a similarity or normalized semantic distance based on the World Wide Web or another large electronic database, for instance Wikipedia, and a search engine that returns reliable aggregate page counts. For…

Information Retrieval · Computer Science 2020-07-24 Andrew R. Cohen , Paul M. B. Vitanyi

In this paper, we establish novel data-dependent upper bounds on the generalization error through the lens of a "variable-size compressibility" framework that we introduce newly here. In this framework, the generalization error of an…

Machine Learning · Statistics 2024-06-12 Milad Sefidgaran , Abdellatif Zaidi

One of the biggest issues in deep learning theory is the generalization ability of networks with huge model size. The classical learning theory suggests that overparameterized models cause overfitting. However, practically used large deep…

Machine Learning · Computer Science 2020-06-23 Taiji Suzuki , Hiroshi Abe , Tomoaki Nishimura

The rise of internet has resulted in an explosion of data consisting of millions of articles, images, songs, and videos. Most of this data is high dimensional and sparse. The need to perform an efficient search for similar objects in such…

Data Structures and Algorithms · Computer Science 2016-12-20 Raghav Kulkarni , Rameshwar Pratap

Traditionally, data compression deals with the problem of concisely representing a data source, e.g. a sequence of letters, for the purpose of eventual reproduction (either exact or approximate). In this work we are interested in the case…

Information Theory · Computer Science 2013-12-10 Amir Ingber , Tsachy Weissman

Data compression is very important feature in terms of saving the memory space. In this proposal, an indexed dictionary based compression is used for text data, where the word's reference in dictionary is used for compression. This approach…

Other Computer Science · Computer Science 2015-12-23 Vivek Dimri , Prof. Ranjit Biswas

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…

Disordered Systems and Neural Networks · Physics 2020-01-08 Francesco Borra , Marco Cosentino Lagomarsino , Pietro Rotondo , Marco Gherardi