Wed Feb 15 2023
Tue Feb 14 2023

Symbolic Discovery of Optimization Algorithms

Deep learning
Optimization algorithms
Deep neural network training
Image classification
Vision-language contrastive learning
Diffusion models
Autoregressive and masked language modeling

Discovers a simple and effective optimization algorithm, Lion, which is more memory-efficient than Adam.

Lion can improve the accuracy of various deep neural network models and save significant pre-training compute. It requires a smaller learning rate than Adam and is particularly effective for large batch sizes.

Universal Guidance for Diffusion Models

Deep learning
Diffusion models
Image processing
Image generation
Universal guidance for diffusion models

Proposes a universal guidance algorithm that enables diffusion models to be controlled by arbitrary guidance modalities without the need to retrain any use-specific components.

The proposed algorithm allows for diffusion models to be controlled by different guidance modalities such as segmentation maps, face recognition, object detection, and classifier signals. It eliminates the need to retrain use-specific components for each modality, making the process more efficient.

Mon Feb 13 2023
Sun Feb 12 2023
Sat Feb 11 2023
Thu Feb 09 2023