Pith. sign in

REVIEW 2 cited by

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy

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 2407.03641 v2 pith:BDGBLRAU submitted 2024-07-04 cs.LG

classification cs.LG
keywords mehl-soupmodelmodelssoupfine-tunedlearned-soupmemorycomputational
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups"~\cite{wortsman2022model} via exploring various hyperparameter configurations.The Learned-Soup, a variant of model soups, significantly improves the performance but suffers from substantial memory and time costs due to the requirements of (i) having to load all fine-tuned models simultaneously, and (ii) a large computational graph encompassing all fine-tuned models. In this paper, we propose Memory Efficient Hyperplane Learned Soup (MEHL-Soup) to tackle this issue by formulating the learned soup as a hyperplane optimization problem and introducing block coordinate gradient descent to learn the mixing coefficients. At each iteration, MEHL-Soup only needs to load a few fine-tuned models and build a computational graph with one combined model. We further extend MEHL-Soup to MEHL-Soup+ in a layer-wise manner. Experimental results on various ViT models and data sets show that MEHL-Soup(+) outperforms Learned-Soup(+) in terms of test accuracy, and also reduces memory usage by more than $13\times$. Moreover, MEHL-Soup(+) can be run on a single GPU and achieves $9\times$ speed up in soup construction compared with the Learned-Soup. The code is released at https://github.com/nblt/MEHL-Soup.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. RanDeS: Randomized Delta Superposition for Multi-Model Compression

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Randomized layer shuffling and column-wise sign flips make interfering task deltas nearly orthogonal, allowing one compressed superset to retrieve near-fine-tuned accuracy for many tasks.

  2. How to Merge Your Multimodal Models Over Time?

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A systematic study of temporal model merging shows that initialization and deployment choices matter far more than the merging technique, with EMA-style weight interpolation as the best practice.

Pith tools