paper-with-me

Papers

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees

2019-05-26 · Maria-Florina Balcan, Tuomas Sandholm, Ellen Vitercik

Algorithms typically come with tunable parameters that have a considerable impact on the computational resources they consume. Too often, practitioners must hand-tune the parameters, a tedious and error-prone task. A recent line of research provides algorithms that return nearly-optimal parameters from within a finite set. These algorithms can be used when the parameter space is infinite by providing as input a random sample of parameters. This data-independent discretization, however, might miss pockets of nearly-optimal parameters: prior research has presented scenarios where the only viable parameters lie within an arbitrarily small region. We provide an algorithm that learns a finite set of promising parameters from within an infinite set. Our algorithm can help compile a configuration portfolio, or it can be used to select the input to a configuration algorithm for finite parameter spaces. Our approach applies to any configuration problem that satisfies a simple yet ubiquitous structure: the algorithm's performance is a piecewise constant function of its parameters. Prior research has exhibited this structure in domains from integer programming to clustering.

📄 PDF Abstract BibTeX arXiv:1905.10819

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control

2025-12-27 · Quang-Hung Bui, Anh Son Ta arxiv

Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($ρ$) an…

FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation

2021-10-16 · Moussa Kamal Eddine, Guokan Shang, Antoine J. -P. Tixier, Michalis Vazirgiannis

Fast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics based on large pretrained language models …

Text GenerationTranslation

FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Fast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics based on large pretrained language models …

Text GenerationTranslation

FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation

2022-05-01 · ACL 2022 5 · Moussa Kamal Eddine, Guokan Shang, Antoine Tixier, Michalis Vazirgiannis

Fast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics based on large pretrained language models …

Text Generation

An Approach to the Frugal Use of Human Annotators to Scale up Auto-coding for Text Classification Tasks

2021-12-01 · ALTA 2021 12 · Li’An Chen, Hanna Suominen

Human annotation for establishing the training data is often a very costly process in natural language processing (NLP) tasks, which has led to frugal NLP approaches becoming an important research topic. Many research te…

text-classificationText Classification