paper-with-me

홈 › Papers

MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks

2021-02-08 · Jaehun Ryu, Hyojin Sung

Deep learning compiler frameworks are gaining ground as a more portable back-end for deep learning applications on increasingly diverse hardware. However, they face the daunting challenge of matching performance offered by hand-tuned target-specific libraries. While auto-tuning frameworks with statistical cost models can provide dynamic and efficient code optimization, they suffer from large space exploration and cost model training overheads. This paper proposes MetaTune, a meta-learning based cost model that more quickly and accurately predicts the performance of optimized codes with pre-trained model parameters. MetaTune encodes convolution kernel codes as structurally similar graphs to facilitate meta-learning, meta-trains a GNN model with a very small input data set, and then predicts optimization parameters for unseen convolution operations with varying sizes and structures during compilation. The resulting framework with MetaTune provides 8 to 13% better inference time on average for four CNN models with comparable or lower optimization time while outperforming transfer learning by 10% in cross-platform cases.

📄 PDF Abstract BibTeX arXiv:2102.04199

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

MetaTune: Adjoint-based Meta-tuning via Robotic Differentiable Dynamics

2026-03-28 · Xiexin Peng, Bingheng Wang, Tao Zhang, Que Dong 외 arxiv

Disturbance observer-based control has shown promise in robustifying robotic systems against uncertainties. However, tuning such systems remains challenging due to the strong coupling between controller gains and observe…

Prompt and Parameter Co-Optimization for Large Language Models

2025-09-29 · Xiaohe Bo, Rui Li, Zexu Sun, Quanyu Dai 외 arxiv

Prompt optimization and fine-tuning are two major approaches to improve the performance of Large Language Models (LLMs). They enhance the capabilities of LLMs from complementary perspectives: the former through explicit …

Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning

2026-05-22 · Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen 외 arxiv

The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data. Exist…

AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning

2024-03-14 · Ruiyi Zhang, Rushi Qiang, Sai Ashish Somayajula, Pengtao Xie

Large-scale pretraining followed by task-specific finetuning has achieved great success in various NLP tasks. Since finetuning all parameters of large pretrained models poses substantial computational and memory challeng…

Meta-LearningNatural Language Understanding

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML

2025-07-30 · Ernesto L. Estevanell-Valladares, Suilan Estevez-Velarde, Yoan Gutiérrez, Andrés Montoyo 외 arxiv

Experts in machine learning leverage domain knowledge to navigate decisions in model selection, hyperparameter optimization, and resource allocation. This is particularly critical for fine-tuning language models (LMs), w…

Hyperparameter OptimizationText Classification