Topic Modelling Black Box Optimization
Roman Akramov, Artem Khamatullin, Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko

TL;DR
This paper compares different black-box optimization methods for selecting the number of topics in LDA, demonstrating that learned optimizers like SABBO and PABBO are more efficient than traditional evolutionary algorithms.
Contribution
It introduces a formulation of topic number selection as a black-box optimization problem and evaluates four optimization strategies, highlighting the efficiency of learned approaches.
Findings
Amortized optimizers reach near-optimal solutions with fewer evaluations.
SABBO identifies good topic numbers after nearly one evaluation.
Learned optimizers outperform evolutionary methods in efficiency.
Abstract
Choosing the number of topics in Latent Dirichlet Allocation (LDA) is a key design decision that strongly affects both the statistical fit and interpretability of topic models. In this work, we formulate the selection of as a discrete black-box optimization problem, where each function evaluation corresponds to training an LDA model and measuring its validation perplexity. Under a fixed evaluation budget, we compare four families of optimizers: two hand-designed evolutionary methods - Genetic Algorithm (GA) and Evolution Strategy (ES) - and two learned, amortized approaches, Preferential Amortized Black-Box Optimization (PABBO) and Sharpness-Aware Black-Box Optimization (SABBO). Our experiments show that, while GA, ES, PABBO, and SABBO eventually reach a similar band of final perplexity, the amortized optimizers are substantially more sample- and time-efficient. SABBO typically…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsText and Document Classification Technologies · Sentiment Analysis and Opinion Mining · Machine Learning and Data Classification
