Tell Me Something New: A New Framework for Asynchronous Parallel Learning - Recommendations

ArXiv: 1805.07483 · DOI: 10.48550/1805.07483

Tell Me Something New: A New Framework for Asynchronous Parallel Learning

Julaiti Alafate, Yoav Freund · Published 2022

We present a novel approach for parallel computation in the context of machine learning that we call "Tell Me Something New" (TMSN). This approach involves a set of independent workers that use broadcast to update each other when they observe "something new". TMSN does not require synchronization or a head node and is highly resilient against failing machines or laggards. We demonstrate the utility of TMSN by applying it to learning boosted trees. We show that our implementation is 10 times faster than XGBoost and LightGBM on the splice-site prediction problem.

View via Publisher Create Alert Cite

Recommendations

Joseph Suarez, Clare Zhu

We present a simple dynamic batching approach applicable to a large class of dynamic architectures that consistently yields speedups of over 10x. We provide performance bounds when the architecture is not known a priori and …

Real-Time Machine Learning: The Missing Pieces

Robert Nishihara, Philipp Moritz, Stephanie Wang, Alexey Tumanov, William Paul, Johann Schleier-Smith, Richard Liaw, Mehrdad Niknami, Michael. I. Jordan, Ion Stoica

Machine learning applications are increasingly deployed not only to serve predictions using static models, but also as tightly-integrated components of feedback loops involving dynamic, real-time decision making. These applications pose a new set of requirements, …

Parameter Database : Data-centric Synchronization for Scalable Machine Learning

Naman Goel, Divyakant Agrawal, Sanjay Chawla, Ahmed Elmagarmid

We propose a new data-centric synchronization framework for carrying out of machine learning (ML) tasks in a distributed environment. Our framework exploits the iterative nature of ML algorithms and relaxes the application agnostic bulk synchronization …

Jasper Zuallaert, Mijung Kim, Yvan Saeys, Wesley De Neve

Thanks to rapidly evolving sequencing techniques, the amount of genomic data at our disposal is growing increasingly large. Determining the gene structure is a fundamental requirement to effectively interpret gene function and regulation. An important …

AIS-MACA- Z: MACA based Clonal Classifier for Splicing Site, Protein Coding and Promoter Region Identification in Eukaryotes

Pokkuluri Kiran Sree, Inampudi Ramesh Babu, SSSN Usha Devi N

Bioinformatics incorporates information regarding biological data storage, accessing mechanisms and presentation of characteristics within this data. Most of the problems in bioinformatics and be addressed efficiently by computer techniques. This paper aims at building a …

Unsupervised Representation Learning of DNA Sequences

Vishal Agarwal, N Jayanth Kumar Reddy, Ashish Anand

Recently several deep learning models have been used for DNA sequence based classification tasks. Often such tasks require long and variable length DNA sequences in the input. In this work, we use a sequence-to-sequence autoencoder …

Romain Azaïs, Florian Ingels

Tree data are ubiquitous because they model a large variety of situations, e.g., the architecture of plants, the secondary structure of RNA, or the hierarchy of XML files. Nevertheless, the analysis of these non-Euclidean data …

CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks

Roberto Dessì, Marco Baroni

Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of "jump around" 0-shot from the component words. Recurrent networks (RNNs) were …

Neural networks with differentiable structure

Thomas Miconi

While gradient descent has proven highly successful in learning connection weights for neural networks, the actual structure of these networks is usually determined by hand, or by other optimization algorithms. Here we describe a simple …

Pokkuluri Kiran Sree, Inampudi Ramesh Babu

Most of the problems in bioinformatics are now the challenges in computing. This paper aims at building a classifier based on Multiple Attractor Cellular Automata (MACA) which uses fuzzy logic. It is strengthened with an …

AIS-MACA- Z: MACA based Clonal Classifier for Splicing Site, Protein Coding and Promoter Region Identification in Eukaryotes

Pokkuluri Kiran Sree, Inampudi Ramesh Babu, SSSN Usha Devi N

Interpretable Convolutional Neural Networks for Effective Translation Initiation Site Prediction

Jasper Zuallaert, Mijung Kim, Yvan Saeys, Wesley De Neve

Recommendations

Overall similar

Similar task

Similar method

Similar dataset