Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors

• URL: http://arxiv.org/abs/2505.00580v1
• Date: Thu, 01 May 2025 15:11:46 GMT
• Title: Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors
• Authors: Xinyu Ding, Lexuan Chen, Siyu Liao, Zhongfeng Wang,
• Abstract summary: We propose to further reduce the complexity by the factorization through the product of interleaved circulant and diagonal matrices.<n>Our method achieves similar or better performance across various tasks with much less floating-point operations (FLOPs) and the number of trainable parameters.
• Score: 8.351342832510262
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models have achieved tremendous success in different domains. However, their huge computation and storage complexity make these models difficult to fine-tune and also less applicable in practice. Recent study shows training in Fourier domain can be an effective fine-tuning method in terms of both model performance and number of training parameters. In this work, we propose to further reduce the complexity by the factorization through the product of interleaved circulant and diagonal matrices. In addition, we address the case of non-square fine-tuning weights by partitioning the circulant matrix into blocks. Our method avoids the construction of weight change matrix and utilizes 1D fast Fourier transform (FFT) instead of 2D FFT. Experimental results show that our method achieves similar or better performance across various tasks with much less floating-point operations (FLOPs) and the number of trainable parameters.

Related papers

• Block Circulant Adapter for Large Language Models [10.353352027807272]
  Fine-tuning large language models (LLMs) is difficult due to their huge model size.<n>Recent Fourier domain-based methods show potential for reducing fine-tuning costs.<n>We propose a block circulant-based matrix fine-tuning method with a stable training to leverage the properties of circulant matrices.
  arXiv  Detail & Related papers  (2025-05-01T15:14:32Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE) RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers. Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers [79.07412045476872]
  Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks.<n>We show that performing the full of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps.<n>We propose a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations.
  arXiv  Detail & Related papers  (2024-12-17T01:12:35Z)
• Sampling Foundational Transformer: A Theoretical Perspective [12.7600763629179]
  We propose Foundational Sampling Transformer (SFT) that can work on multiple data modalities. SFT has achieved competitive results on many benchmarks, while being faster in inference, compared to other very specialized models.
  arXiv  Detail & Related papers  (2024-08-11T16:53:09Z)
• Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis [63.66763657191476]
  We show that efficient numerical training and inference algorithms as low-rank computation have impressive performance for learning Transformer-based adaption. We analyze how magnitude-based models affect generalization while improving adaption. We conclude that proper magnitude-based has a slight on the testing performance.
  arXiv  Detail & Related papers  (2024-06-24T23:00:58Z)
• Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization [102.92240148504774]
  We study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT)
  arXiv  Detail & Related papers  (2023-11-10T18:59:54Z)
• Parameter Efficient Multi-task Model Fusion with Partial Linearization [97.23530944186078]
  We propose a novel method to improve multi-task fusion for parameter-efficient fine-tuning techniques. Our approach partially linearizes only the adapter modules and applies task arithmetic over the linearized adapters. We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model.
  arXiv  Detail & Related papers  (2023-10-07T08:55:54Z)
• Large-Scale Learning with Fourier Features and Tensor Decompositions [3.6930948691311007]
  We exploit the tensor product structure of deterministic Fourier features, which enables us to represent the model parameters as a low-rank tensor decomposition. We demonstrate by means of numerical experiments how our low-rank tensor approach obtains the same performance of the corresponding nonparametric model.
  arXiv  Detail & Related papers  (2021-09-03T14:12:53Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.