A LLM Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Автор: AutoML Seminars

Загружено: 2025-07-31

Просмотров: 690

Описание:

Title: LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Speakers:
Elena Raponi: https://www.universiteitleiden.nl/en/...
Niki van Stein: https://www.universiteitleiden.nl/en/...

Paper:
LLaMEABO: https://arxiv.org/abs/2505.21034
LLaMEA: https://ieeexplore.ieee.org/abstract/...

Abstract:
Large Language Models (LLMs) are rapidly becoming creative co-pilots for AI, Optimization and AutoML, moving beyond tuning to generating and evolving entire algorithms on demand. This talk introduces LLaMEA, an evolutionary computation framework that uses LLMs to iteratively mutate and improve full codebases, generating competitive optimizers across continuous, combinatorial, and hyperparameter spaces. We specifically focus on its application to Bayesian Optimization (LLaMEA-BO), showing how LLM-generated code, guided by adapted prompt engineering and mutation schedules, consistently discovers high-performing BO algorithms and scales well across dimensions and tasks. The talk also covers integration with AutoML toolchains, insights from the BLADE benchmarking suite, and offers practical takeaways with open-source code.

A LLM Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

Chronos: Time series forecasting in the age of pretrained models

Chronos: Time series forecasting in the age of pretrained models

TabArena: A Living Benchmark for Machine Learning on Tabular Data

TabArena: A Living Benchmark for Machine Learning on Tabular Data

From Principles to Practice: How to Get Involved in the Ai4Nature Alliance

From Principles to Practice: How to Get Involved in the Ai4Nature Alliance

Hyperband-based Bayesian Optimization for Efficient Black-box Prompt Selection

Hyperband-based Bayesian Optimization for Efficient Black-box Prompt Selection

Станислав Белковский*: Персонально ваш / 22.01.26 @BelkovskiyS

Станислав Белковский*: Персонально ваш / 22.01.26 @BelkovskiyS

Do-PFN: In-Context Learning for Causal Effect Estimation

Do-PFN: In-Context Learning for Causal Effect Estimation

Accurate predictions on small data (and time series) with the tabular foundation model TabPFN

Accurate predictions on small data (and time series) with the tabular foundation model TabPFN

Киев без отопления после атаки. Кто вошел в «Совет мира» Трампа. К Путину летят Уиткофф и Кушнер

Киев без отопления после атаки. Кто вошел в «Совет мира» Трампа. К Путину летят Уиткофф и Кушнер

AutoML in the Age of Structured Foundation Models

AutoML in the Age of Structured Foundation Models

Самая сложная модель из тех, что мы реально понимаем

Самая сложная модель из тех, что мы реально понимаем

Доработайте свою степень магистра права за 13 минут. Вот как

Доработайте свою степень магистра права за 13 минут. Вот как

Understanding High-Dimensional Bayesian Optimization

Understanding High-Dimensional Bayesian Optimization

Manuel Delanda,

Manuel Delanda, "Deleuze and the Use of the Genetic Algorithm in Architecture"

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Превратите ЛЮБОЙ файл в знания LLM за СЕКУНДЫ

Превратите ЛЮБОЙ файл в знания LLM за СЕКУНДЫ

Запуск нейросетей локально. Генерируем - ВСЁ

Запуск нейросетей локально. Генерируем - ВСЁ

Can AI Improve Itself? [Chris Lu, Robert Lange, Cong Lu]

Can AI Improve Itself? [Chris Lu, Robert Lange, Cong Lu]

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Accelerating Bayesian Inference and Data Acquisition via Amortization

Accelerating Bayesian Inference and Data Acquisition via Amortization

Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization

Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization