A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Generalization Guarantees for Neural Architecture Search with Train-Validation Split
[article]
2022
arXiv
pre-print
Preserved Fulltext
Other Versions
Neural Architecture Search (NAS) is a popular method for automatically designing optimized architectures for high-performance deep learning. ...
Extensions to transfer learning are developed in terms of the mismatch between training & validation distributions. (2) We establish generalization bounds for NAS problems with an emphasis on an activation ...
(TVO)
Generalization with Train-Validation Split In this section we state our generic generalization bounds for bilevel optimization problems with trainvalidation split. ...
arXiv:2104.14132v3
fatcat:ftc4qbwzkvbn7liexpaohiwkyy
JMSNAS: Joint Model Split and Neural Architecture Search for Learning over Mobile Edge Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, a joint model split and neural architecture search (JMSNAS) framework is proposed to automatically generate and deploy a DNN model over a mobile edge network. ...
Considering both the computing and communication resource constraints, a computational graph search problem is formulated to find the multi-split points of the DNN model, and then the model is trained ...
split and neural architecture search (JMSNAS) framework for deploying an ML model over the MEC. ...
arXiv:2111.08206v1
fatcat:6xzcdzzqbbfthmnwjo6hrtocze
Differentially-private Federated Neural Architecture Search
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress ...
To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable architecture by exchanging gradients of architecture variables ...
To this end, we study federated neural architecture search (FNAS), where multiple parties collaboratively search for an optimal neural architecture without exchanging sensitive data with each other for ...
arXiv:2006.10559v2
fatcat:7xpjs4bc6rf5nj6ljle4mnzdpm
Evaluating volumetric and slice-based approaches for COVID-19 detection in chest CTs
2021
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
on the validation subset. ...
Our best results reach a macro F1 score of 92.34% on the validation subset and 90.06% on the test set, obtained with the volumetric approach which was ranked second in the competition. ...
Thus, one model is trained on the official train-validation split for 150 epochs whereas other 4 models are trained on 4 in-house generated folds for 100 epochs. ...
doi:10.1109/iccvw54120.2021.00065
fatcat:aommhqelsnb45hpokfnfkv3e74
Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose an efficient NAS framework that is trained once on a database consisting of datasets and pretrained networks and can rapidly search for a neural architecture for a novel dataset ...
mostly tackled the optimization of searching for the network architecture for a single task (dataset), which does not generalize well across multiple tasks (datasets). ...
Acknowledgements This work was conducted by Center for Applied Research in Artificial Intelligence (CARAI) grant funded by DAPA and ADD (UD190031RD). ...
arXiv:2107.00860v1
fatcat:nmi3nfy7cjhz5kdrk37gh67hou
Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
This study aims at making the architecture search process more adaptive for one-shot or online training. ...
This study introduces a growing mechanism for differentiable neural architecture search based on network morphism. ...
train (w, α) (3) The second sub-optimization is generally a normal training process of model parameters with training data, while the first one is optimized on validation set and can be done with finite ...
arXiv:2106.07211v1
fatcat:7idiaskyirgnznh73lvgwngofi
Continual Learning with Guarantees via Weight Interval Constraints
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. ...
any firm guarantees that network performance will not deteriorate uncontrollably over time. ...
The main idea is to constrain the parameter search within the set of parameters for which any particular solution is valid for the previous tasks. ...
arXiv:2206.07996v1
fatcat:yiqoubkgwnazjmstjakotbvmpq
DC-NAS: Divide-and-Conquer Neural Architecture Search
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Neural architecture searching is a way of automatically exploring optimal deep neural networks in a given huge search space. ...
In contrast to conventional methods, here we present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures. ...
Thus, for a given parameter K, the RS method randomly selects 156 + K different neural architectures from the search space, and the architectures are fully trained to obtain the validation result. ...
arXiv:2005.14456v1
fatcat:4pledk4txjefhg4tu6gz2h5v7i
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
[article]
2021
IEEE Transactions on Software Engineering
accepted
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2009.00437v3 fatcat:tjnyxvjpmjgwdbpli2xqm4jhdyOther Versions
for both aspects of the neural architectures. ...
NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets. ...
We hope to use the proposed splits to unify the training, validation and test sets for a fairer comparison. ...
doi:10.1109/tpami.2021.3054824
pmid:33497330
arXiv:2009.00437v5
fatcat:skeqlmissvdxfiaclgyfr5gujy
Towards Privacy-Preserving Neural Architecture Search
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To address these issues, we propose a privacy-preserving neural architecture search (PP-NAS) framework based on secure multi-party computation to protect users' data and the model's parameters/hyper-parameters ...
However, massive user data collected for training deep learning models raises privacy concerns and increases the difficulty of manually adjusting the network structure. ...
NAS Search for CNN The NAS paradigm aims to automatically search for the optimal network architecture that leads to the best validation accuracy or efficiency with time and resource constraints. ...
arXiv:2204.10958v1
fatcat:ta7neeob4newdgridsdvcxz73i
Neural Differential Equations for Single Image Super-resolution
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The adjoint method previously proposed for gradient estimation has no theoretical stability guarantees; we find a practical case where this makes it unusable, and show that discrete sensitivity analysis ...
Inspired by variational methods for image restoration relying on partial differential equations, we choose to benchmark several forms of Neural DEs and backpropagation methods on single image super-resolution ...
Architecture search on the BSD dataset As this smaller dataset allows an extensive grid architecture search, we identify the best-performing differential system on the BSD dataset before moving on to DIV2K ...
arXiv:2005.00865v1
fatcat:xrelxw76vbg33nehz5lnjhn37i
Single Path One-Shot Neural Architecture Search with Uniform Sampling
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We revisit the one-shot Neural Architecture Search (NAS) paradigm and analyze its advantages over existing NAS approaches. ...
All architectures (and their weights) are trained fully and equally. Comprehensive experiments verify that our approach is flexible and effective. It is easy to train and fast to search. ...
We randomly split the original training set into two parts: 50000 images are for validation (50 images for each class exactly) and the rest as the training set. ...
arXiv:1904.00420v4
fatcat:inacuybierd3bboe5aguisrf74
Competitive neural trees for pattern classification
1998
IEEE Transactions on Neural Networks
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper introduces different search methods for the CNeT, which are utilized for training as well as for recall. ...
This paper presents competitive neural trees (CNeT's) for pattern classification. The CNeT contains m m m-ary nodes and grows during learning by using inheritance to initialize new nodes. ...
The neural tree architectures reported in the literature can be grouped according to the learning paradigm employed for their training. ...
doi:10.1109/72.728387
pmid:18255815
fatcat:i2qpxp6icvglrpaa63thih5n4q
A scalable constructive algorithm for the optimization of neural network architectures
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same ...
by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete. ...
Vladimir Protopopescu for his valuable feedback in the preparation of this manuscript and three anonymous reviewers for their very useful comments and suggestions. ...
arXiv:1909.03306v3
fatcat:5z6yt2i4pvhvpo2pgokt5gvfsa
Simplifying Architecture Search for Graph Neural Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To overcome these drawbacks, we propose the SNAG framework (Simplified Neural Architecture search for Graph neural networks), consisting of a novel search space and a reinforcement learning based search ...
To obtain optimal data-specific GNN architectures, researchers turn to neural architecture search (NAS) methods, which have made impressive progress in discovering effective architectures in convolutional ...
For all datasets, We split the nodes in all graphs into 60%, 20%, 20% for training, validation, and test. For the transductive task, we use the classification accuracy as the evaluation metric. ...
arXiv:2008.11652v2
fatcat:7mgbknvplvcsxoh3mcs3ofhduy
« Previous
Showing results 1 — 15 out of 19,290 results