AutoML Seminars Courses

Understanding High-Dimensional Bayesian Optimization

Explore the challenges and solutions in high-dimensional Bayesian optimization, focusing on why simple methods succeed and how vanishing gradients affect performance in real-world applications.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

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

Discover HbBoPs framework combining Gaussian process surrogates with Hyperband for sample-efficient black-box prompt selection in large language models across API-only settings.

• YouTube
• 48 minutes
• Self-Paced
• Free Video

FunBO - Discovering Acquisition Functions for Bayesian Optimization with FunSearch

Discover how FunSearch extends to Bayesian optimization through FunBO, a novel method for identifying efficient acquisition functions that outperform traditional approaches in optimization problems.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

TabArena - A Living Benchmark for Machine Learning on Tabular Data

Discover TabArena, a continuously maintained benchmarking system for tabular machine learning that compares deep learning, gradient-boosted trees, and foundation models across datasets.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

A LLM Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

Discover how LLMs can automatically generate and evolve Bayesian optimization algorithms through evolutionary computation, creating competitive optimizers across various problem spaces.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

Large Language Models to Enhance Bayesian Optimization

Discover how Large Language Models enhance Bayesian optimization through LLAMBO, improving hyperparameter tuning and black-box function optimization with natural language integration.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

The AI Scientist - Towards Fully Automated Open-Ended Scientific Discovery

Explore groundbreaking research on autonomous AI systems capable of conducting end-to-end scientific discovery, from generating ideas to writing papers and performing peer reviews in machine learning.

• YouTube
• 52 minutes
• Self-Paced
• Free Video

Searching for Neural Architectures from Fundamental Operations - An Introduction to einspace

Explore neural architecture search through einspace, a novel approach using fundamental operations to discover diverse and competitive network architectures for machine learning tasks.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Mixture-of-Supernets - Improving Weight-Sharing Supernet Training with Architecture-Routed MoE

Explore cutting-edge research on Mixture-of-Supernets architecture that enhances neural architecture search efficiency and improves BERT and MT model performance through innovative weight-sharing techniques.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Vanilla Bayesian Optimization Performs Great in High Dimensions

Discover how scaling Gaussian process lengthscale prior with dimensionality enables vanilla Bayesian optimization to excel in high-dimensional optimization problems, outperforming complex alternatives.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Multi-objective Differentiable Neural Architecture Search

Explore advanced techniques in neural architecture optimization across multiple objectives and hardware devices, focusing on Pareto front profiling and hypernetwork-based solutions.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

Neural Fine-Tuning Search for Few-Shot Learning

Explore advanced neural architecture search techniques for optimizing few-shot learning adaptation strategies, focusing on meta-training and meta-testing trade-offs in multi-domain contexts.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Is Mamba Capable of In-Context Learning? - An Analysis of State Space Models

Explore how Mamba, a state space model, demonstrates in-context learning capabilities comparable to transformers while handling longer input sequences more efficiently in AI applications.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

Discover a methodology for efficiently selecting and fine-tuning pretrained models through meta-learning, optimizing model selection and hyperparameter configurations for new datasets.

• YouTube
• 40 minutes
• Self-Paced
• Free Video

OmniPred - Towards Universal Regressors with Language Models

Explore groundbreaking research on OmniPred's innovative approach to using language models as universal regressors, demonstrating superior performance over traditional regression methods across diverse experiments.

• YouTube
• 49 minutes
• Self-Paced
• Free Video