
Sign up to save your podcasts
Or
This paper compares cosine annealing and infinite learning rate schedules for continual self-supervised learning, finding the latter more effective in enhancing pre-training performance across various datasets.
https://arxiv.org/abs//2503.02844
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
5
33 ratings
This paper compares cosine annealing and infinite learning rate schedules for continual self-supervised learning, finding the latter more effective in enhancing pre-training performance across various datasets.
https://arxiv.org/abs//2503.02844
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
696 Listeners
199 Listeners
289 Listeners
76 Listeners
441 Listeners