PulseAugur
EN
LIVE 19:45:31

New dataset BBO-Pile advances foundation models for black-box optimization

By PulseAugur Editorial · [4 sources] ·

Researchers have introduced BBO-Pile, a novel open-source dataset containing over 500,000 optimization trajectories across nearly 3,100 black-boxes. This dataset aims to address the limitations of previous work, which relied on non-public or synthetic data, thereby hindering reproducibility and real-world generalization. By using BBO-Pile, foundation models for black-box optimization have been trained at various scales, demonstrating the effectiveness of large-scale pre-training for imitating optimization methods. AI

IMPACT Enables more reproducible and generalizable research in black-box optimization by providing a large-scale, open-source dataset.

RANK_REASON The cluster contains multiple academic papers detailing new datasets and methods for black-box optimization.

Read on arXiv cs.NE (Neural & Evolutionary) →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

COVERAGE [4]

  1. arXiv cs.LG TIER_1 · Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien, David Salinas ·

    An Open-Source Training Dataset for Foundation Models for Black-box Optimization

    arXiv:2605.23417v1 Announce Type: new Abstract: Most black-box optimization methods require extensive hyperparameter tuning, often limiting their ability to generalize across different optimization domains. Foundation models for black-box optimization that learn optimization prin…

  2. arXiv cs.LG TIER_1 · David Salinas ·

    An Open-Source Training Dataset for Foundation Models for Black-box Optimization

    Most black-box optimization methods require extensive hyperparameter tuning, often limiting their ability to generalize across different optimization domains. Foundation models for black-box optimization that learn optimization principles from a large collection of optimization t…

  3. arXiv cs.LG TIER_1 · Azza Fadhel, The Hung Tran, Trong Nghia Hoang, Jana Doppa ·

    Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks

    arXiv:2604.12325v3 Announce Type: replace Abstract: We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past experimental data. A key challenge in this setting is data scarcity: in many scien…

  4. arXiv cs.NE (Neural & Evolutionary) TIER_1 · Shengkun Chang ·

    Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization

    Existing Meta-Black-Box Optimization (MetaBBO) methods focus on how to search when controlling optimizers, but largely overlook where to search. We propose MetaSG-SAEA, a bi-level MetaBBO framework for expensive constrained multi-objective optimization problems (ECMOPs), in which…

RELATED ENTITIES

RELATED TOPICS