MétaCan
Menu
Back to cohort
Record W4399304331 · doi:10.1145/3650200.3656619

Sylva: Sparse Embedded Adapters via Hierarchical Approximate Second-Order Information

2024· article· en· W4399304331 on OpenAlexaff
Baorun Mu, Christina Giannoula, Gennady Pekhimenko

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicBlind Source Separation Techniques
Canadian institutionsVector InstituteUniversity of Toronto
Fundersnot available
KeywordsComputer scienceOrder (exchange)Theoretical computer scienceArtificial intelligenceMathematics

Abstract

fetched live from OpenAlex

Fine-tuning is the gateway to transferring learned knowledge in a pre-trained Large Language Model (LLM) on many downstream applications. To make LLM fine-tuning more affordable, prior works follow two paths: i) adapters freeze the pre-trained LLM weights and inject a small number of trainable weights during fine-tuning, and ii) pruners remove the less important weights in pre-trained LLMs and train the remaining sparse weights during fine-tuning. We find that the former introduces computation overheads due to the injected trainable parameters, while the latter introduces an expensive pre-processing step to identify the important weights and degrades model quality. To get the best of both worlds, we propose Sylva, a novel LLM fine-tuning procedure that provides high system performance during fine-tuning and attains state-of-the-art model quality on downstream applications. Sylva identifies the most important LLM weights via second-order information in a pre-processing step, and significantly reduces the computation and storage costs of the pre-processing step via i) a hierarchical approximation of second-order information, and ii) an online projection and rediagonalization algorithm. Sylva trains only the sparse important weights and embeds these sparse weights into the pre-trained LLM during fine-tuning to provide high system performance. We show that end-to-end fine-tuning with Sylva is, on average, 5.1 × faster than ZeRO and 1.2 × faster than LoRA, the state-of-the-art adapter approach. Sylva’s hierarchical approximation reduces the peak GPU memory in the pre-processing step by 2.3 × compared to K-FAC, the most widely used approximation to second-order information. The source code of Sylva is publicly available at https://github.com/CentML/Sylva.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.874
Threshold uncertainty score0.658

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.003
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.249
Teacher spread0.237 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicBlind Source Separation TechniquesFrench-language works237,207