Guardado en:
Detalles Bibliográficos
Autores principales: Verma, Chetan, Timmaraju, Aditya Srinivas, Hsieh, Cho-Jui, Damle, Suyash, Bui, Ngot, Zhang, Yang, Chen, Wen, Liu, Xin, Jain, Prateek, Dhillon, Inderjit S
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.23337
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918226674319360
author Verma, Chetan
Timmaraju, Aditya Srinivas
Hsieh, Cho-Jui
Damle, Suyash
Bui, Ngot
Zhang, Yang
Chen, Wen
Liu, Xin
Jain, Prateek
Dhillon, Inderjit S
author_facet Verma, Chetan
Timmaraju, Aditya Srinivas
Hsieh, Cho-Jui
Damle, Suyash
Bui, Ngot
Zhang, Yang
Chen, Wen
Liu, Xin
Jain, Prateek
Dhillon, Inderjit S
contents Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose MatTA, a framework for training multiple accurate Student models using a novel Teacher-TA-Student recipe. TA models are larger versions of the Student models with higher capacity, and thus allow Student models to better relate to the Teacher model and also bring in more domain-specific expertise. Furthermore, multiple accurate Student models can be extracted from the TA model. Therefore, despite only one training run, our methodology provides multiple servable options to trade off accuracy for lower serving cost. We demonstrate the proposed method, MatTA, on proprietary datasets and models. Its practical efficacy is underscored by live A/B tests within a production ML system, demonstrating 20% improvement on a key metric. We also demonstrate our method on GPT-2 Medium, a public model, and achieve relative improvements of over 24% on SAT Math and over 10% on the LAMBADA benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23337
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Matryoshka Model Learning for Improved Elastic Student Models
Verma, Chetan
Timmaraju, Aditya Srinivas
Hsieh, Cho-Jui
Damle, Suyash
Bui, Ngot
Zhang, Yang
Chen, Wen
Liu, Xin
Jain, Prateek
Dhillon, Inderjit S
Machine Learning
Artificial Intelligence
Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose MatTA, a framework for training multiple accurate Student models using a novel Teacher-TA-Student recipe. TA models are larger versions of the Student models with higher capacity, and thus allow Student models to better relate to the Teacher model and also bring in more domain-specific expertise. Furthermore, multiple accurate Student models can be extracted from the TA model. Therefore, despite only one training run, our methodology provides multiple servable options to trade off accuracy for lower serving cost. We demonstrate the proposed method, MatTA, on proprietary datasets and models. Its practical efficacy is underscored by live A/B tests within a production ML system, demonstrating 20% improvement on a key metric. We also demonstrate our method on GPT-2 Medium, a public model, and achieve relative improvements of over 24% on SAT Math and over 10% on the LAMBADA benchmark.
title Matryoshka Model Learning for Improved Elastic Student Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.23337