A general approach to progressive learning

By Joshua T. Vogelstein, Hayden S. Helm, Ronak D. Mehta, Jayanta Dey, Weiwei Yang, Bryan Tower, Will LeVine, Jonathan Larson, Christoper M. White, Christopher M. White and 1 more. 2020

10 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Carey E. Priebe
2. Brandon Duderstadt
3. Youngser Park
4. Ronak D. Mehta
5. Joshua T. Vogelstein
6. Hayden S. Helm
7. Aranyak Acharyya

Citations in the corpus

• Tracking the perspectives of interacting language models (2024, background): “Our work is closely related to simulating groups of computational agents to study sociological and cultural phenomena (Steels, 1990; Wagner et al., 2003) and to continual learning (Vogelstein et al., 2020; Geisa et al., 2021).”
• A partition-based similarity for classification distributions (2020, methodology): “We evaluate the efficacy of a transfer learning algorithm via transfer efficiency (Vogelstein et al., 2020): TE(h n , h T n ) := E [ RFT ( h n ) )] /E [ RFT ( hn )]”
• Inducing a hierarchy for multi-class classification problems (2021, unknown): “The Learning Efficiency (LE) (Vogelstein et al., 2020) of hn relative to h′n for a given n is the ratio of the corresponding risks: LE(hn, h ′ n) = RF (hn) RF (h′n) .”