Pith. sign in

REVIEW

Confounding Tradeoffs for Neural Network Quantization

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 2102.06366 v1 pith:6DOYVROY submitted 2021-02-12 cs.LG cs.CV

classification cs.LGcs.CV
keywords quantizationtradeoffsconfoundingimpactmethodsnetworkaccelerationaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Many neural network quantization techniques have been developed to decrease the computational and memory footprint of deep learning. However, these methods are evaluated subject to confounding tradeoffs that may affect inference acceleration or resource complexity in exchange for higher accuracy. In this work, we articulate a variety of tradeoffs whose impact is often overlooked and empirically analyze their impact on uniform and mixed-precision post-training quantization, finding that these confounding tradeoffs may have a larger impact on quantized network accuracy than the actual quantization methods themselves. Because these tradeoffs constrain the attainable hardware acceleration for different use-cases, we encourage researchers to explicitly report these design choices through the structure of "quantization cards." We expect quantization cards to help researchers compare methods more effectively and engineers determine the applicability of quantization techniques for their hardware.

Discussion (0). Continue with ORCID to comment.

Pith tools