Pith. sign in

REVIEW 5 cited by

The Expressive Power of Low-Rank Adaptation

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 2310.17513 v3 pith:QRLTVU7Z submitted 2023-10-26 cs.LG cs.AIcs.CLstat.ML

classification cs.LGcs.AIcs.CLstat.ML
keywords loramodeltextadaptationlow-rankmodelsdepthexpressive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method that leverages low-rank adaptation of weight matrices, has emerged as a prevalent technique for fine-tuning pre-trained models such as large language models and diffusion models. Despite its huge success in practice, the theoretical underpinnings of LoRA have largely remained unexplored. This paper takes the first step to bridge this gap by theoretically analyzing the expressive power of LoRA. We prove that, for fully connected neural networks, LoRA can adapt any model $f$ to accurately represent any smaller target model $\overline{f}$ if LoRA-rank $\geq(\text{width of }f) \times \frac{\text{depth of }\overline{f}}{\text{depth of }f}$. We also quantify the approximation error when LoRA-rank is lower than the threshold. For Transformer networks, we show any model can be adapted to a target model of the same size with rank-$(\frac{\text{embedding size}}{2})$ LoRA adapters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. The impact of allocation strategies in subset learning on the expressive power of neural networks

    cs.LG 2025-02 conditional novelty 7.0 of 10

    In a teacher-student setup, maximal expressive power for a fixed learnable-weight budget is characterized by even row or column distribution in linear RNNs and feedforward networks.

  2. HRP: High-Rank Preheating for Superior LoRA Initialization

    cs.LG 2025-02 conditional novelty 6.0 of 10

    HRP initializes LoRA with the top singular vectors of a briefly preheated high-rank adapter, improving fine-tuning results over random initialization in experiments.

  3. Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection

    cs.LG 2026-07 conditional novelty 5.0 of 10

    LoRA fine-tuning has Θ~(rd/n) sample complexity, and over-ranking strictly hurts unregularized empirical risk minimization while being harmless for nuclear-norm-style adaptive estimators.

  4. MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detection

    cs.SD 2025-09 conditional novelty 5.0 of 10

    MoLEx combines LoRA adapters with a top-K expert router inside a frozen WavLM model, achieving 5.56% EER on ASVSpoof 5 without augmentation.

  5. Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Fine-tuned time-series foundation models, especially Chronos with LoRA, outperform trained-from-scratch deep forecasters on multi-signal building energy forecasting with limited data.

Pith tools