Neural Network Quantization by Learning Low-Loss Subspaces
This paper proposes a novel neural network quantization method that learns quantization-aware linear paths to find midpoints in low-loss subspaces, achieving performance comparable to quantization-aware training without using the straight-through estimator or explicit discretization during training.
[2606.25087] Neural Network Quantization by Learning Low-Loss Subspaces
[Submitted on 23 Jun 2026]
Title:Neural Network Quantization by Learning Low-Loss Subspaces
View a PDF of the paper titled Neural Network Quantization by Learning Low-Loss Subspaces, by Vladimir Protsenko and 3 other authors
View PDF
Abstract:Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithfully as possible. Enforcing discrete constraints perturbs parameters away from a well-optimized minimum, generally resulting in performance degradation. Recent studies indicate that low-loss FP solutions are not isolated, but instead belong to connected low-loss subspaces of the loss landscape, where the loss maintains nearly the same minimum value. Models sampled from these subspaces are diverse and retain high accuracy. This raises the question: can a quantized model be constructed to lie within a low-loss subspace of the FP model, thereby automatically preserving performance? We address this question by learning quantization-aware linear paths in weight space optimized to minimize loss. We demonstrate that the midpoint of the resulting subspace is, by design, quantization-friendly and that its direct quantization yields performance comparable to that of quantization-aware training. The proposed procedure offers a novel perspective on weight quantization and, in contrast to conventional methods, neither relies on the straight-through estimator nor involves explicit discretization during training.
Comments: 30 pages, 7 figures
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2606.25087 [cs.CV]
(or arXiv:2606.25087v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.25087
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Vladimir Protsenko [view email] [v1] Tue, 23 Jun 2026 18:48:45 UTC (8,257 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Neural Network Quantization by Learning Low-Loss Subspaces, by Vladimir Protsenko and 3 other authors
View PDF
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)