paper-with-me

Papers

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization

2025-04-14 · Timur Carstensen, Neeratyoy Mallik, Frank Hutter, Martin Rapp

As model sizes grow, finding efficient and cost-effective hyperparameter optimization (HPO) methods becomes increasingly crucial for deep learning pipelines. While multi-fidelity HPO (MF-HPO) trades off computational resources required for DL training with lower fidelity estimations, existing fidelity sources often fail under lower compute and memory constraints. We propose a novel fidelity source: the number of layers that are trained or frozen during training. For deep networks, this approach offers significant compute and memory savings while preserving rank correlations between hyperparameters at low fidelities compared to full model training. We demonstrate this in our empirical evaluation across ResNets and Transformers and additionally analyze the utility of frozen layers as a fidelity in using GPU resources as a fidelity in HPO, and for a combined MF-HPO with other fidelity sources. This contribution opens new applications for MF-HPO with hardware resources as a fidelity and creates opportunities for improved algorithms navigating joint fidelity spaces.

📄 PDF Abstract BibTeX arXiv:2504.10735

Code (0)

등록된 구현이 없습니다.

Tasks

GPUHyperparameter Optimization

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

Analysis of memory consumption by neural networks based on hyperparameters

2021-10-21 · Mahendran N

Deep learning models are trained and deployed in multiple domains. Increasing usage of deep learning models alarms the usage of memory consumed while computation by deep learning models. Existing approaches for reducing …

Deep LearningModel Compression

Understanding Is Done Early: A Depth Division of Labor in Large Language Models and Its Use for Unbounded-Context Memory

2026-07-30 · Hanzuo Liu, Xuan Qi, Chunyu Liu, Haotian Zhong 외 arxiv

Transformer depth is not used uniformly: lower and middle layers build semantic representations, while upper layers increasingly specialize them for prediction. We turn this division of labor into CoMem (Comprehension Me…

Learning Plug-and-play Memory for Guiding Video Diffusion Models

2025-11-24 · Selena Song, Ziming Xu, Zijun Zhang, Kun Zhou 외 arxiv

Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical laws and commonsense dynamics, revealing …

Video Generation

Frozen in Time: Parameter-Efficient Time Series Transformers via Reservoir-Induced Feature Expansion and Fixed Random Dynamics

2025-08-25 · Pradeep Singh, Mehak Sharma, Anupriya Dey, Balasubramanian Raman arxiv

Transformers are the de-facto choice for sequence modelling, yet their quadratic self-attention and weak temporal bias can make long-range forecasting both expensive and brittle. We introduce FreezeTST, a lightweight hyb…

FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

2026-06-18 · Yuhwan Jeong, Hyeonseong Kim, Daehyun We, Seonkyu Song 외 arxiv

Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fi…

Autonomous DrivingData AugmentationScene Generation