English
Related papers

Related papers: The Condition Number as a Scale-Invariant Proxy fo…

200 papers

This paper proposes a novel entropy encoding technique for lossless data compression. Representing a message string by its lexicographic index in the permutations of its symbols results in a compressed version matching Shannon entropy of…

Information Theory · Computer Science 2017-03-24 Abu Bakar Siddique

We study the following one-way asymmetric transmission problem, also a variant of model-based compressed sensing: a resource-limited encoder has to report a small set $S$ from a universe of $N$ items to a more powerful decoder (server). The…

Data Structures and Algorithms · Computer Science 2018-07-30 Alexandr Andoni , Javad Ghaderi , Daniel Hsu , Dan Rubenstein , Omri Weinstein

A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to optimize performance on training data when the real objective…

Machine Learning · Statistics 2018-02-16 Matías Vera , Pablo Piantanida , Leonardo Rey Vega

Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Ufuk Can Biçici , Cem Keskin , Lale Akarun

State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption. This has created a recent demand for memory-efficient optimizers. To this end, we investigate the limits and…

Machine Learning · Computer Science 2019-02-14 Xinyi Chen , Naman Agarwal , Elad Hazan , Cyril Zhang , Yi Zhang

In this paper, we consider contention resolution algorithms that are augmented with predictions about the network. We begin by studying the natural setup in which the algorithm is provided a distribution defined over the possible network…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-27 Seth Gilbert , Calvin Newport , Nitin Vaidya , Alex Weaver

The information plane (Tishby et al. arXiv:physics/0004057, Shwartz-Ziv et al. arXiv:1703.00810) has been proposed as an analytical tool for studying the learning dynamics of neural networks. It provides quantitative insight on how the…

Quantum Physics · Physics 2024-11-05 Nathan Haboury , Mo Kordzanganeh , Alexey Melnikov , Pavel Sekatski

In the high-dimensional data setting, the sample covariance matrix is singular. In order to get a numerically stable and positive definite modification of the sample covariance matrix in the high-dimensional data setting, in this paper we…

Numerical Analysis · Mathematics 2021-01-20 Shaoxin Wang

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error.…

Machine Learning · Computer Science 2019-08-08 Roozbeh Yousefzadeh , Dianne P O'Leary

The performance of a lossy data compression scheme for uniformly biased Boolean messages is investigated via methods of statistical mechanics. Inspired by a formal similarity to the storage capacity problem in the research of neural…

Statistical Mechanics · Physics 2009-11-07 T. Hosaka , Y. Kabashima , H. Nishimori

After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…

Machine Learning · Computer Science 2022-10-18 Jerry Chee , Megan Renz , Anil Damle , Christopher De Sa

This work proposes a mathematically founded mixed precision accumulation strategy for the inference of neural networks. Our strategy is based on a new componentwise forward error analysis that explains the propagation of errors in the…

Machine Learning · Computer Science 2025-12-03 El-Mehdi El Arar , Silviu-Ioan Filip , Theo Mary , Elisa Riccietti

Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Zongyu Guo , Zhizheng Zhang , Runsen Feng , Zhibo Chen

Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description lengths of previous data…

Machine Learning · Computer Science 2020-06-29 Xu He , Min Lin

Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer's toolkit. While many have striven to improve the…

Computation and Language · Computer Science 2023-04-25 Tim van Dam , Maliheh Izadi , Arie van Deursen

Scalability properties of deep neural networks raise key research questions, particularly as the problems considered become larger and more challenging. This paper expands on the idea of conditional computation introduced by Bengio, et.…

Machine Learning · Computer Science 2014-01-30 Andrew Davis , Itamar Arel

Higher-order information theory has become a rapidly growing toolkit in computational neuroscience, motivated by the idea that multivariate dependencies can reveal aspects of neural computation and communication that are invisible to…

Neurons and Cognition · Quantitative Biology 2025-12-03 D. Rebbin , K. J. A. Down , T. F. Varley , R. Ince , A. Canales-Johnson

Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from limited data. The widely adopted Chinchilla scaling law…

Machine Learning · Computer Science 2026-05-05 Justin Lovelace , Christian Belardi , Srivatsa Kundurthy , Shriya Sudhakar , Kilian Q. Weinberger

Analog models of quantum information processing, such as adiabatic quantum computation and analog quantum simulation, require the ability to subject a system to precisely specified Hamiltonians. Unfortunately, the hardware used to implement…

Quantum Physics · Physics 2014-02-25 Kevin C. Young , Robin Blume-Kohout , Daniel A. Lidar
‹ Prev 1 3 4 5 6 7 10 Next ›