Methods › General › Ternarization › Ternary Weight Splitting

Ternary Weight Splitting

2 papers tagged archive 2025-07-28

Introduced by Haoli Bai et al. in BinaryBERT: Pushing the Limit of BERT Quantization

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Ternary Weight Splitting is a ternarization approach used in BinaryBERT that exploits the flatness of ternary loss landscape as the optimization proxy of the binary model. We first train the half-sized ternary BERT to convergence, and then split both the latent full-precision weight wᵗ and quantized ŵᵗ to their binary counterparts w₁ᵇ, w₂ᵇ and ŵ₁ᵇ, ŵ₂ᵇ via the TWS operator. To inherit the performance of the ternary model after splitting, the TWS operator requires the splitting equivalency (i.e., the same output given the same input):

wᵗ=w₁ᵇ+w₂ᵇ, ŵᵗ=ŵ₁ᵇ+ŵ₂ᵇ

While solution to the above equation is not unique, we constrain the latent full-precision weights after splitting w₁ᵇ, w₂ᵇ to satisfy wᵗ=w₁ᵇ+w₂ᵇ. See the paper for more details.

PaperSource

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: Weight Mixup; Ternary Mamba; Weight Weaving; weight scaling; weight operators; Weight Balancing; Weight Recycling; sample splitting.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 2 · with a code link: 1 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 2 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 2 of 2, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Quantization2
Binarization1
Model Compression1
Scheduling1

Usage over time archive 2025-07-28

Papers per year tagged with Ternary Weight Splitting: 2020 to 2024, peak 1 1 0 2020: 1 paper 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (2 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Ternarization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections