Paper Citation Record · LEDGER

Accelerated CNN Training Through Gradient Approximation

As of 14 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:1908.05460.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
1908.05460 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T13:16:42.284264Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

33 of 33 outbound references displayed

verified exact4
verified fuzzy11
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7983f3b1-cdf4-4db8-bf40-ba9e0102f779 · outbound

This paper cites Tensorﬂow: A system for large-scale machine learning.

Accelerated CNN Training Through Gradient Approximation Tensorﬂow: A system for large-scale machine learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.099777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31af04a7-cb31-496d-a8cd-ee3b94c15c51 · outbound

This paper cites Faster Neural Network Training with Approximate Tensor Operations.

Accelerated CNN Training Through Gradient Approximation Faster Neural Network Training with Approximate Tensor Operations

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-14T13:16:42.744748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0e85f209-f582-4381-8085-7ed962bb8db3 · outbound

This paper cites Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes.

Accelerated CNN Training Through Gradient Approximation Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.112438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51723726-9f5c-4b01-9052-96c327c0b38e · outbound

This paper cites Assessing the scalability of biologically-motivated deep learning algo- rithms and architectures.

Accelerated CNN Training Through Gradient Approximation Assessing the scalability of biologically-motivated deep learning algo- rithms and architectures

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.959217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91e53907-8f7d-47e3-bbf9-5df0ef954482 · outbound

This paper cites Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs.

Accelerated CNN Training Through Gradient Approximation Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.123375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2ae8905-b22e-44de-b3e8-eddb5ff4c89c · outbound

This paper cites cuDNN: Efficient Primitives for Deep Learning.

Accelerated CNN Training Through Gradient Approximation cuDNN: Efficient Primitives for Deep Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.129369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f091178e-2f58-42ea-bcab-d9738141dc0e · outbound

This paper cites Full deep neural network training on a pruned weight budget.

Accelerated CNN Training Through Gradient Approximation Full deep neural network training on a pruned weight budget

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.135559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7cd2657-ae21-438b-9044-a5b75219df34 · outbound

This paper cites Submanifold Sparse Convolutional Networks.

Accelerated CNN Training Through Gradient Approximation Submanifold Sparse Convolutional Networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.142188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f0d28b1-b772-444c-a4ab-a5e4b562527f · outbound

This paper cites CondenseNet: An Efficient DenseNet using Learned Group Convolutions.

Accelerated CNN Training Through Gradient Approximation CondenseNet: An Efficient DenseNet using Learned Group Convolutions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.151217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f3ba43b-b01f-4f79-ae4a-712a5543bfc7 · outbound

This paper cites Efficient Convolutional Neural Network Training with Direct Feedback Alignment.

Accelerated CNN Training Through Gradient Approximation Efficient Convolutional Neural Network Training with Direct Feedback Alignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.156740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d90145f-eef0-4d49-b8d7-a525451618fe · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

Accelerated CNN Training Through Gradient Approximation Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.162140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14abb1f-c29f-43e6-906e-32acff717243 · outbound

This paper cites Deep residual learning for image recognition.

Accelerated CNN Training Through Gradient Approximation Deep residual learning for image recognition

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.167926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e960d7-d28f-4df4-8983-d0b934e3da5f · outbound

This paper cites Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.

Accelerated CNN Training Through Gradient Approximation Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.173980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89362087-01b3-42d1-bae3-464b631693ea · outbound

This paper cites Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes.

Accelerated CNN Training Through Gradient Approximation Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.179210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01ee53d-90ef-4e0e-a8d0-76bc1b98fde5 · outbound

This paper cites In-datacenter per- formance analysis of a tensor processing unit.

Accelerated CNN Training Through Gradient Approximation In-datacenter per- formance analysis of a tensor processing unit

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.932388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 591d4183-f787-4242-9beb-fef6d808d01c · outbound

This paper cites Learning multiple layers of features from tiny images.

Accelerated CNN Training Through Gradient Approximation Learning multiple layers of features from tiny images

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.189783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575a2363-3490-48a7-8e61-45ea86cb9b54 · outbound

This paper cites Random synaptic feedback weights support error backpropagation for deep learning.

Accelerated CNN Training Through Gradient Approximation Random synaptic feedback weights support error backpropagation for deep learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.902270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91be7638-96d5-4028-b44c-559d83b2cdb8 · outbound

This paper cites Efficient Sparse-Winograd Convolutional Neural Networks.

Accelerated CNN Training Through Gradient Approximation Efficient Sparse-Winograd Convolutional Neural Networks

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-14T13:16:42.510234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f3a616b6-bc4a-4994-a190-80a78a97a071 · outbound

This paper cites PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration.

Accelerated CNN Training Through Gradient Approximation PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-14T13:16:42.475638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7a1f96b1-5249-406a-9446-a614e1ed6d7a · outbound

This paper cites Nvidia tensor core pro- grammability, performance & precision.

Accelerated CNN Training Through Gradient Approximation Nvidia tensor core pro- grammability, performance & precision

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.884296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d2e23773-3dda-4671-8d47-181378aba173 · outbound

This paper cites Mixed Precision Training.

Accelerated CNN Training Through Gradient Approximation Mixed Precision Training

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.215383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8103b93a-4f6f-4aac-a32b-655a54f98442 · outbound

This paper cites Direct feedback alignment provides learning in deep neural networks.

Accelerated CNN Training Through Gradient Approximation Direct feedback alignment provides learning in deep neural networks

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.867883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b1c53001-d8c0-4f9c-afc9-b881a6cb1417 · outbound

This paper cites Faster CNNs with Direct Sparse Convolutions and Guided Pruning.

Accelerated CNN Training Through Gradient Approximation Faster CNNs with Direct Sparse Convolutions and Guided Pruning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.226280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91242104-9158-4d41-bc59-5831165d8e54 · outbound

This paper cites Sbnet: Sparse blocks network for fast inference.

Accelerated CNN Training Through Gradient Approximation Sbnet: Sparse blocks network for fast inference

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.850406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1a545ae2-9a96-4ae5-b738-c389316f6481 · outbound

This paper cites Very Deep Convolutional Networks for Large-Scale Image Recognition.

Accelerated CNN Training Through Gradient Approximation Very Deep Convolutional Networks for Large-Scale Image Recognition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.236265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08af80e6-dcfe-4b67-8567-d858551a38b4 · outbound

This paper cites meprop: Sparsiﬁed back propagation for accelerated deep learning with reduced overﬁtting.

Accelerated CNN Training Through Gradient Approximation meprop: Sparsiﬁed back propagation for accelerated deep learning with reduced overﬁtting

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.831866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6b8c0fac-8cda-4774-a70d-9374af2d9bc8 · outbound

This paper cites Training simpliﬁcation and model simpliﬁcation for deep learning: A minimal effort back propagation method.IEEE Transactions on Knowledge and Data Engineering, 2018.

Accelerated CNN Training Through Gradient Approximation Training simpliﬁcation and model simpliﬁcation for deep learning: A minimal effort back propagation method.IEEE Transactions on Knowledge and Data Engineering, 2018

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.814552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d89334ce-7185-4ad0-9dbc-76a2cb57f197 · outbound

This paper cites Gra- dient sparsiﬁcation for communication-efﬁcient distributed optimization.

Accelerated CNN Training Through Gradient Approximation Gra- dient sparsiﬁcation for communication-efﬁcient distributed optimization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.797835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 86399129-5caa-4169-aff1-c223faea57c5 · outbound

This paper cites Minimal Effort Back Propagation for Convolutional Neural Networks.

Accelerated CNN Training Through Gradient Approximation Minimal Effort Back Propagation for Convolutional Neural Networks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.258733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3612027-5bfd-46c5-8fe0-781580d70229 · outbound

This paper cites Terngrad: Ternary gradi- ents to reduce communication in distributed deep learning.

Accelerated CNN Training Through Gradient Approximation Terngrad: Ternary gradi- ents to reduce communication in distributed deep learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.780206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e0c687f7-e52f-483e-ae86-2f82a2ed6b85 · outbound

This paper cites Biologically-plausible learning algorithms can scale to large datasets.

Accelerated CNN Training Through Gradient Approximation Biologically-plausible learning algorithms can scale to large datasets

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-14T13:16:42.270519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911a5974-972a-4e8a-8187-b416a1ff5684 · outbound

This paper cites Imagenet training in minutes.

Accelerated CNN Training Through Gradient Approximation Imagenet training in minutes

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T13:16:42.761777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e1c89aeb-b8db-488b-b27f-015afa22fb7c · outbound

This paper cites Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training.

Accelerated CNN Training Through Gradient Approximation Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-14T13:16:42.341246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

No inbound Pith citation observations are available.