Pith. sign in

REVIEW 1 cited by

Nerva: a Truly Sparse Implementation of Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.17437 v1 pith:KJJEEYQR submitted 2024-07-24 cs.LG

classification cs.LG
keywords nervapytorchsparselibrarymasksneuralsparsityaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We introduce Nerva, a fast neural network library under development in C++. It supports sparsity by using the sparse matrix operations of Intel's Math Kernel Library (MKL), which eliminates the need for binary masks. We show that Nerva significantly decreases training time and memory usage while reaching equivalent accuracy to PyTorch. We run static sparse experiments with an MLP on CIFAR-10. On high sparsity levels like $99\%$, the runtime is reduced by a factor of $4\times$ compared to a PyTorch model using masks. Similar to other popular frameworks such as PyTorch and Keras, Nerva offers a Python interface for users to work with.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Dynamic sparse training of multiple heads on a shared backbone outperforms full dense ensembles on ImageNet and C4 while using less compute.

Pith tools