A Study of the Optimization Algorithms in Deep Learning
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Training the deep learning models involves learning of the parameters to meet the objective function. Typically the objective is to minimize the loss incurred during the learning process. In a supervised mode of learning, a model is given the data samples and their respective outcomes. When a model generates an output, it compares it with the desired output and then takes the difference of generated and desired outputs and then attempts to bring the generated output close to the desired output. This is achieved through optimization algorithms. An optimization algorithm goes through several cycles until convergence to improve the accuracy of the model. There are several types of optimization methods developed to address the challenges associated with the learning process. Six of these have been taken up to be examined in this study to gain insights about their intricacies. The methods investigated are stochastic gradient descent, nesterov momentum, rmsprop, adam, adagrad, adadelta. Four datasets have been selected to perform the experiments which are mnist, fashionmnist, cifar10 and cifar100. The optimal training results obtained for mnist is 1.00 with RMSProp and adam at epoch 200, fashionmnist is 1.00 with rmsprop and adam at epoch 400, cifar10 is 1.00 with rmsprop at epoch 200, cifar100 is 1.00 with adam at epoch 100. The highest testing results are achieved with adam for mnist, fashionmnist, cifar10 and cifar100 are 0.9826, 0.9853, 0.9855, 0.9842 respectively. The analysis of results shows that adam optimization algorithm performs better than others at testing phase and rmsprop and adam at training phase.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“[7] discusses the adam algorithm.”
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108 · cited 1×
“[9] has developed the fashion mnist dataset.”
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322 · cited 1×
“[5] presents a modification of adagrad into adadelta.”
BackgroundAn overview of gradient descent optimization algorithms
Ruder, S. (2016) · arXiv · doi:10.48550/arxiv.1609.04747 · Cited by 4,962 · cited 1×
“[1] discusses gradient descent and its variants.”
Incorporating Nesterov Momentum into Adam
Dozat, T. (2016) · Cited by 1,595
Variants of RMSProp and Adagrad with Logarithmic Regret BoundsPreprint
Mukkamala, M. C., & Hein, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05507 · Cited by 308 · cited 1×
“[6] discusses the rmsprop and its variants.”
Learning rate schedules for faster stochastic gradient search
Darken, C., Chang, J., & Moody, J. (2003) · Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop · doi:10.1109/nnsp.1992.253713 · Cited by 212 · cited 1×
“Its variant is stochastic gradient descent [3] that performs the training on the individual data element.”
Background
Metadata
- Authors
- Zaheer, R., & Shaziya, H.
- Venue
- 2019 Third International Conference on Inventive Systems and Control (ICISC)
- Publisher
- IEEE
- Published
- 2019-01
- Pages
- 536-539
- OpenAlex
- W3012135218
- Cited by
- 164
- References
- 7
- FWCI
- 3.51
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.