@inproceedings{nguyen-etal-2025-sharpness,
title = "Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations",
author = "Nguyen, Tung and
Le, Tue and
Vuong, Hoang Tran and
Nguyen, Quang Duc and
Nguyen, Duc Anh and
Van, Linh Ngo and
Dinh, Sang and
Nguyen, Thien Huu",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.231/",
doi = "10.18653/v1/2025.naacl-long.231",
pages = "4507--4524",
ISBN = "979-8-89176-189-6",
abstract = "Recent advanced frameworks in topic models have significantly enhanced the performance compared to conventional probabilistic approaches. Such models, mostly constructed from neural network architecture together with other advanced techniques such as contextual embedding, optimal transport distance and pre-trained language model, etc. have effectively improved the topic quality and document topic distribution. Despite the improvements, these methods lack considerations of effective optimization for complex objective functions that contain log-likelihood and additional regularization terms. In this study, we propose to apply an efficient optimization method to improve the generalization and performance of topic models. Our approach explicitly considers the sharpness of the loss landscape during optimization, which forces the optimizer to choose directions in the parameter space that lead to flatter minima, in which the models are typically more stable and robust to small perturbations in the data. Additionally, we propose an effective strategy to select the flatness region for parameter optimization by leveraging the optimal transport distance between doc-topic distributions and doc-cluster proportions, which can effectively enhance document representation. Experimental results on popular benchmark datasets demonstrate that our method effectively improves the performance of baseline topic models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-sharpness">
<titleInfo>
<title>Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tue</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="given">Tran</namePart>
<namePart type="family">Vuong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quang</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="given">Ngo</namePart>
<namePart type="family">Van</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Recent advanced frameworks in topic models have significantly enhanced the performance compared to conventional probabilistic approaches. Such models, mostly constructed from neural network architecture together with other advanced techniques such as contextual embedding, optimal transport distance and pre-trained language model, etc. have effectively improved the topic quality and document topic distribution. Despite the improvements, these methods lack considerations of effective optimization for complex objective functions that contain log-likelihood and additional regularization terms. In this study, we propose to apply an efficient optimization method to improve the generalization and performance of topic models. Our approach explicitly considers the sharpness of the loss landscape during optimization, which forces the optimizer to choose directions in the parameter space that lead to flatter minima, in which the models are typically more stable and robust to small perturbations in the data. Additionally, we propose an effective strategy to select the flatness region for parameter optimization by leveraging the optimal transport distance between doc-topic distributions and doc-cluster proportions, which can effectively enhance document representation. Experimental results on popular benchmark datasets demonstrate that our method effectively improves the performance of baseline topic models.</abstract>
<identifier type="citekey">nguyen-etal-2025-sharpness</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.231</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.231/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>4507</start>
<end>4524</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations
%A Nguyen, Tung
%A Le, Tue
%A Vuong, Hoang Tran
%A Nguyen, Quang Duc
%A Nguyen, Duc Anh
%A Van, Linh Ngo
%A Dinh, Sang
%A Nguyen, Thien Huu
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F nguyen-etal-2025-sharpness
%X Recent advanced frameworks in topic models have significantly enhanced the performance compared to conventional probabilistic approaches. Such models, mostly constructed from neural network architecture together with other advanced techniques such as contextual embedding, optimal transport distance and pre-trained language model, etc. have effectively improved the topic quality and document topic distribution. Despite the improvements, these methods lack considerations of effective optimization for complex objective functions that contain log-likelihood and additional regularization terms. In this study, we propose to apply an efficient optimization method to improve the generalization and performance of topic models. Our approach explicitly considers the sharpness of the loss landscape during optimization, which forces the optimizer to choose directions in the parameter space that lead to flatter minima, in which the models are typically more stable and robust to small perturbations in the data. Additionally, we propose an effective strategy to select the flatness region for parameter optimization by leveraging the optimal transport distance between doc-topic distributions and doc-cluster proportions, which can effectively enhance document representation. Experimental results on popular benchmark datasets demonstrate that our method effectively improves the performance of baseline topic models.
%R 10.18653/v1/2025.naacl-long.231
%U https://aclanthology.org/2025.naacl-long.231/
%U https://doi.org/10.18653/v1/2025.naacl-long.231
%P 4507-4524
Markdown (Informal)
[Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations](https://aclanthology.org/2025.naacl-long.231/) (Nguyen et al., NAACL 2025)
ACL
- Tung Nguyen, Tue Le, Hoang Tran Vuong, Quang Duc Nguyen, Duc Anh Nguyen, Linh Ngo Van, Sang Dinh, and Thien Huu Nguyen. 2025. Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4507–4524, Albuquerque, New Mexico. Association for Computational Linguistics.