Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic masking

Inigo Urteaga | Moulay Zaidane Draidia | Tomer Lancewicki | Shahram Khadivi |

Paper Details:

Month: July
Year: 2023
Location: Toronto, Canada
Venue: F | i | n | d | i | n | g | s | - | A | C | L |