Search · four archives

Results for mini-batch learning

or ask it as a questionAsk the stacks →

ArchivesarXiv PubMed bioRxiv chemRxiv

WhenAny time Past month Past year Past 5 years

OrderMost relevant Most cited Newest

18 papers · ranked by Valyu relevance

01
AarXiv20 Apr 2018
Revisiting Small Batch Training for Deep Neural Networks
Dominic Masters, Carlo Luschi
Modern deep neural network training is typically based on mini-batch stochastic gradient optimization. While the use of large mini-batches increases the available computational parallelism, small batch training has been shown to provide improved generalization performance and allows a significantly smaller memory…
91relevance
02
PPubMed10 Jan 2022
Mini-batch optimization enables training of ODE models on large-scale datasets
Paul Stapor, Leonard Schmiester, Christoph Wierling, Simon Merkt + 4 more
Quantitative dynamic models are widely used to study cellular signal processing. A critical step in modelling is the estimation of unknown model parameters from experimental data. As model sizes and datasets are steadily growing, established parameter optimization approaches for mechanistic models become…
89relevance
03
BbioRxiv30 Nov 2019
Mini-batch optimization enables training of ODE models on large-scale datasets
Paul Stapor, Leonard Schmiester, Christoph Wierling, Bodo M.H. Lange + 2 more
Quantitative dynamical models are widely used to study cellular signal processing. A critical step in modeling is the estimation of unknown model parameters from experimental data. As model sizes and datasets are steadily growing, established parameter optimization approaches for mechanistic models become…
85relevance
04
PPubMed5 Sep 2019
An approach on the implementation of full batch, online and mini-batch learning on a Mamdani based neuro-fuzzy system with center-of-sets defuzzification: Analysis and evaluation about its functionality, performance, and behavior An approach on the implementation of full batch, online and mini-batch learning on a neuro-fuzzy system
Sukey Nakasima-López, Juan R. Castro, Mauricio A. Sanchez, Olivia Mendoza + 2 more
'Olivia Mendoza' 'Antonio Rodríguez-Díaz' 'Jie Zhang'] Due to the rapid technological evolution and communications accessibility, data generated from different sources of information show an exponential growth behavior. That is, volume of data samples that need to be analyzed are getting larger, so the methods for its…
85relevance
05
AarXiv18 Oct 2019
Improving the convergence of SGD via adaptive batch sizes
Scott Sievert
Mini-batch stochastic gradient descent (SGD) and variants thereof approximate the objective function's gradient with a small number of training examples, aka the batch size. Small batch sizes require little computation for each model update but can yield high-variance gradient estimates, which poses some challenges for…
84relevance
06
AarXiv18 Jun 2017
Gradient Diversity Empowers Distributed Learning: Convergence and Stability of Mini-batch SGD
Dong Yin, Ashwin Pananjady, Max W. Y. Lam, Dimitris Papailiopoulos + 2 more
'Kannan Ramchandran' 'Peter L. Bartlett'] It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size. In this work, we present an analysis hinting that high…
84relevance
07
AarXiv2023
Can we learn better with hard samples?
Subin Sahayam, John Zakkam, Umarani Jayaraman
In deep learning, mini-batch training is commonly used to optimize network parameters. However, the traditional mini-batch method may not learn the under-represented samples and complex patterns in the data, leading to a longer time for generalization. To address this problem, a variant of the traditional algorithm has…
83relevance
08
PPubMed2 Feb 2026
Uncovering Latent Structures: A Bayesian Approach to Estimating Q-Matrix and Attribute Hierarchies in Cognitive Diagnostic Models
Xue Wang, Yinghan Chen, Shiyu Wang
Cognitive diagnostic models (CDMs) provide fine-grained diagnostic feedback by modeling the relationship between latent attributes and item responses. Two key components required for CDM implementation are the Q-matrix, which links items to attributes, and the attribute hierarchy, which defines prerequisite…
83relevance
09
AarXiv2021
Micro Batch Streaming: Allowing the Training of DNN Models to Use a large Batch Size in Memory Constrained Environments
XinYu Piao, DoangJoo Synn, Jooyoung Park, Jong‐Kook Kim
Recent deep learning models are difficult to train using a large batch size, because commodity machines may not have enough memory to accommodate both the model and a large data batch size. The batch size is one of the hyper-parameters used in the training model, and it is dependent on and is limited by the target…
79relevance
10
AarXiv2013
Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients
Tom Schaul, Yann LeCun
Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on stationary problems, and permitting learning rates to grow appropriately in…
78relevance
11
BbioRxiv27 May 2020
mbkmeans: fast clustering for single cell data using mini-batch *k*-means
Stephanie C. Hicks, Ruoxi Liu, Yuwei Ni, Elizabeth Purdom + 1 more
Single-cell RNA-Sequencing (scRNA-seq) is the most widely used high-throughput technology to measure genome-wide gene expression at the single-cell level. One of the most common analyses of scRNA-seq data detects distinct subpopulations of cells through the use of unsupervised clustering algorithms. However, recent…
77relevance
12
PPubMed2 Nov 2023
Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems
Hyeonseong Choi, Byung Hyun Lee, Se Young Chun, Jaehwan Lee + 1 more
'Elena Loli Piccolomini'] Modern deep neural networks cannot be often trained on a single GPU due to large model size and large data size. Model parallelism splits a model for multiple GPUs, but making it scalable and seamless is challenging due to different information sharing among GPUs with communication overhead.…
76relevance
13
BbioRxiv17 Jan 2020
Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning
Chao Gao, Joshua D. Welch
Recent experimental advances have enabled high-throughput single-cell measurement of gene expression, chromatin accessibility and DNA methylation. We previously used integrative non-negative matrix factorization (iNMF) to jointly learn interpretable low-dimensional representations from multiple single-cell datasets…
73relevance
14
CchemRxiv3 Oct 2023
FAME.AL: Site-of-metabolism prediction with active learning
Ya Chen, Thomas Seidel, Roxane Axel Jacob, Steffen Hirte + 6 more
The ability to determine and predict metabolically labile atom positions in a molecule (also called “sites of metabolism” or “SoMs”) is of high interest to the design and optimization of bioactive compounds such as drugs, agrochemicals, and cosmetics. In recent years, several in silico models for SoM prediction have…
73relevance
15
BbioRxiv29 Jul 2023
Deep Batch Active Learning for Drug Discovery
Michael Bailey, Saeed Moayedpour, Ruijiang Li, Alejandro Corrochano-Navarro + 10 more
A key challenge in drug discovery is to optimize, in silico, various absorption and affinity properties of small molecules. One strategy that was proposed for such optimization process is active learning. In active learning molecules are selected for testing based on their likelihood of improving model performance. To…
71relevance
16
PPubMed20 Sep 2021
Insights into few shot learning approaches for image scene classification
Mohamed Soudy, Yasmine Afify, Nagwa Badr, Yilun Shang
Image understanding and scene classification are keystone tasks in computer vision. The development of technologies and profusion of existing datasets open a wide room for improvement in the image classification and recognition research area. Notwithstanding the optimal performance of exiting machine learning models in…
63relevance
17
CchemRxiv10 Jul 2025
LifeLong Learning for Large Language Models in Predicting Chemical Reaction Yields
Authors not listed
Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike…
60relevance
18
CchemRxiv30 Jun 2021
Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction
Simon Viet Johansson, Hampus Gummesson Svensson, Esben Bjerrum, Alexander Schliep + 3 more
Computer aided synthesis planning is a rapidly growing field for suggesting synthetic routes for molecules of interest. The methods used are usually dependent on access to large datasets for training, but with a finite experimental budget there are limitations on how much data can be obtained from experiments. Active…
55relevance

Results for mini-batch learning

Revisiting Small Batch Training for Deep Neural Networks

Mini-batch optimization enables training of ODE models on large-scale datasets

Mini-batch optimization enables training of ODE models on large-scale datasets

Improving the convergence of SGD via adaptive batch sizes

Gradient Diversity Empowers Distributed Learning: Convergence and Stability of Mini-batch SGD

Can we learn better with hard samples?

Uncovering Latent Structures: A Bayesian Approach to Estimating Q-Matrix and Attribute Hierarchies in Cognitive Diagnostic Models

Micro Batch Streaming: Allowing the Training of DNN Models to Use a large Batch Size in Memory Constrained Environments

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

mbkmeans: fast clustering for single cell data using mini-batch k-means

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning

FAME.AL: Site-of-metabolism prediction with active learning

Deep Batch Active Learning for Drug Discovery

Insights into few shot learning approaches for image scene classification

LifeLong Learning for Large Language Models in Predicting Chemical Reaction Yields

Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction

Revisiting Small Batch Training for Deep Neural Networks

Mini-batch optimization enables training of ODE models on large-scale datasets

Mini-batch optimization enables training of ODE models on large-scale datasets

Improving the convergence of SGD via adaptive batch sizes

Gradient Diversity Empowers Distributed Learning: Convergence and Stability of Mini-batch SGD

Can we learn better with hard samples?

Uncovering Latent Structures: A Bayesian Approach to Estimating Q-Matrix and Attribute Hierarchies in Cognitive Diagnostic Models

Micro Batch Streaming: Allowing the Training of DNN Models to Use a large Batch Size in Memory Constrained Environments

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

mbkmeans: fast clustering for single cell data using mini-batch k-means

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning

FAME.AL: Site-of-metabolism prediction with active learning

Deep Batch Active Learning for Drug Discovery

Insights into few shot learning approaches for image scene classification

LifeLong Learning for Large Language Models in Predicting Chemical Reaction Yields

Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction

Results for mini-batch learning

Revisiting Small Batch Training for Deep Neural Networks

Mini-batch optimization enables training of ODE models on large-scale datasets

Mini-batch optimization enables training of ODE models on large-scale datasets

Improving the convergence of SGD via adaptive batch sizes

Gradient Diversity Empowers Distributed Learning: Convergence and Stability of Mini-batch SGD

Can we learn better with hard samples?

Uncovering Latent Structures: A Bayesian Approach to Estimating Q-Matrix and Attribute Hierarchies in Cognitive Diagnostic Models

Micro Batch Streaming: Allowing the Training of DNN Models to Use a large Batch Size in Memory Constrained Environments

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

mbkmeans: fast clustering for single cell data using mini-batch *k*-means

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning

FAME.AL: Site-of-metabolism prediction with active learning

Deep Batch Active Learning for Drug Discovery

Insights into few shot learning approaches for image scene classification

LifeLong Learning for Large Language Models in Predicting Chemical Reaction Yields

Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction

Revisiting Small Batch Training for Deep Neural Networks

Mini-batch optimization enables training of ODE models on large-scale datasets

Mini-batch optimization enables training of ODE models on large-scale datasets

Improving the convergence of SGD via adaptive batch sizes

Gradient Diversity Empowers Distributed Learning: Convergence and Stability of Mini-batch SGD

Can we learn better with hard samples?

Uncovering Latent Structures: A Bayesian Approach to Estimating Q-Matrix and Attribute Hierarchies in Cognitive Diagnostic Models

Micro Batch Streaming: Allowing the Training of DNN Models to Use a large Batch Size in Memory Constrained Environments

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

mbkmeans: fast clustering for single cell data using mini-batch *k*-means

Towards accelerating model parallelism in distributed deep learning systems Towards accelerating model parallelism in distributed deep learning systems

Iterative Refinement of Cellular Identity from Single-Cell Data Using Online Learning

FAME.AL: Site-of-metabolism prediction with active learning

Deep Batch Active Learning for Drug Discovery

Insights into few shot learning approaches for image scene classification

LifeLong Learning for Large Language Models in Predicting Chemical Reaction Yields

Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction

mbkmeans: fast clustering for single cell data using mini-batch k-means

mbkmeans: fast clustering for single cell data using mini-batch k-means