paper-with-me

홈 › Papers

HOFT: Householder Orthogonal Fine-tuning

2025-05-22 · Alejandro Moreno Arcas, Albert Sanchis, Jorge Civera, Alfons Juan

Adaptation of foundation models using low-rank methods is a widespread approach. Another way to adapt these models is to employ orthogonal fine-tuning methods, which are less time and memory efficient despite their good generalization properties. In this work, we propose Householder Orthogonal Fine-tuning (HOFT), a novel orthogonal fine-tuning method that aims to alleviate time and space complexity. Moreover, some theoretical properties of the orthogonal fine-tuning paradigm are explored. From this exploration, Scaled Householder Orthogonal Fine-tuning (SHOFT) is proposed. Both HOFT and SHOFT are evaluated in downstream tasks, namely commonsense reasoning, machine translation, subject-driven generation and mathematical reasoning. Compared with state-of-the-art adaptation methods, HOFT and SHOFT show comparable or better results.

📄 PDF Abstract BibTeX arXiv:2505.16531

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationMathematical Reasoning

Similar Papers 제목 키워드 기반

Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation

2024-05-24 · Shen Yuan, Haotian Liu, Hongteng Xu

While following different technical routes, both low-rank and orthogonal adaptation techniques can efficiently adapt large-scale pre-training models in specific tasks or domains based on a small piece of trainable parame…

Householder Projector for Unsupervised Latent Semantics Discovery

2023-07-16 · ICCV 2023 1 · Yue Song, Jichao Zhang, Nicu Sebe, Wei Wang

Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space. Latent semantics discovery methods emerge to move around the late…

Exploring the Limitations of Structured Orthogonal Dictionary Learning

2025-01-25 · Anirudh Dash, Aditya Siripuram

This work is motivated by recent applications of structured dictionary learning, in particular when the dictionary is assumed to be the product of a few Householder atoms. We investigate the following two problems: 1) Ho…

Dictionary Learning

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

2026-05-12 · Lanxin Zhao, Bamdev Mishra, Pratik Jawanpuria, Lequan Lin 외 arxiv

Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in wh…

parameter-efficient fine-tuningMathematical Reasoning

Fast Structured Orthogonal Dictionary Learning using Householder Reflections

2024-09-13 · Anirudh Dash, Aditya Siripuram

In this paper, we propose and investigate algorithms for the structured orthogonal dictionary learning problem. First, we investigate the case when the dictionary is a Householder matrix. We give sample complexity result…

Dictionary Learning