Salvato in:
Dettagli Bibliografici
Autori principali: Dey, Prasanjit, Dev, Soumyabrata, Schoen-Phelan, Bianca
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.29756
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910089849339904
author Dey, Prasanjit
Dev, Soumyabrata
Schoen-Phelan, Bianca
author_facet Dey, Prasanjit
Dev, Soumyabrata
Schoen-Phelan, Bianca
contents We address the challenge of adapting pre-trained Large Language Models (LLMs) for multivariate time-series analysis, where their deployment is often hindered by prohibitive computational and memory demands. Our solution, One-for-All, introduces Gaussian Rank-Stabilized Low-Rank Adapters (rsLoRA) to enable parameter-efficient fine-tuning of frozen LLMs. While inspired by LoRA, rsLoRA introduces a mathematically grounded rank-stabilization mechanism that enables provable gradient stability at low ranks a novel contribution absent in prior PEFT methods. Our framework injects trainable rank decomposition matrices (rank 16) into positional embeddings and output layers, while keeping self-attention weights fixed. This design reduces trainable parameters by 6.8$\times$ (vs. TimesNet), 21$\times$ (vs. GPT4TS), and 11.8$\times$ (vs. TIME-LLM), while achieving a 168-1,776$\times$ smaller memory footprint (2.2MiB vs. 340MiB-4.18GiB in SOTA models). Rigorous evaluation across six time-series tasks demonstrates that One-for-All achieves state-of-the-art efficiency-accuracy trade-offs: 5.5$\times$ higher parameter efficiency (MSE=5.50) than TimesNet and 21$\times$ better than GPT4TS, while matching their forecasting accuracy (MSE=0.33). The framework's stability is validated through consistent performance across diverse horizons (96-720 steps) and datasets (ETT, Weather, M3, M4), with 98.3% fewer parameters than conventional transformers. These advances enable deployment on edge devices for healthcare, finance, and environmental monitoring without compromising performance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29756
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle One-for-All: A Lightweight Stabilized and Parameter-Efficient Pre-trained LLM for Time Series Forecasting
Dey, Prasanjit
Dev, Soumyabrata
Schoen-Phelan, Bianca
Machine Learning
We address the challenge of adapting pre-trained Large Language Models (LLMs) for multivariate time-series analysis, where their deployment is often hindered by prohibitive computational and memory demands. Our solution, One-for-All, introduces Gaussian Rank-Stabilized Low-Rank Adapters (rsLoRA) to enable parameter-efficient fine-tuning of frozen LLMs. While inspired by LoRA, rsLoRA introduces a mathematically grounded rank-stabilization mechanism that enables provable gradient stability at low ranks a novel contribution absent in prior PEFT methods. Our framework injects trainable rank decomposition matrices (rank 16) into positional embeddings and output layers, while keeping self-attention weights fixed. This design reduces trainable parameters by 6.8$\times$ (vs. TimesNet), 21$\times$ (vs. GPT4TS), and 11.8$\times$ (vs. TIME-LLM), while achieving a 168-1,776$\times$ smaller memory footprint (2.2MiB vs. 340MiB-4.18GiB in SOTA models). Rigorous evaluation across six time-series tasks demonstrates that One-for-All achieves state-of-the-art efficiency-accuracy trade-offs: 5.5$\times$ higher parameter efficiency (MSE=5.50) than TimesNet and 21$\times$ better than GPT4TS, while matching their forecasting accuracy (MSE=0.33). The framework's stability is validated through consistent performance across diverse horizons (96-720 steps) and datasets (ETT, Weather, M3, M4), with 98.3% fewer parameters than conventional transformers. These advances enable deployment on edge devices for healthcare, finance, and environmental monitoring without compromising performance.
title One-for-All: A Lightweight Stabilized and Parameter-Efficient Pre-trained LLM for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2603.29756