Search Results for author:
Found 3 papers, 0 papers with code
A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation
In particular, we explore knowledge distillation and learning rate heuristics of (cosine) restarts and warmup using mode connectivity and CCA.
Using Mode Connectivity for Loss Landscape Analysis
Mode connectivity is a recently introduced frame- work that empirically establishes the connected- ness of minima by finding a high accuracy curve between two independently trained models.
Unsupervised robust nonparametric learning of hidden community properties
We consider learning of fundamental properties of communities in large noisy networks, in the prototypical situation where the nodes or users are split into two classes according to a binary property, e. g., according to their opinions or preferences on a topic.
