Rohan's Bytes

Rohan's Bytes

Share this post

Rohan's Bytes
Rohan's Bytes
ML Interview Q Series: Why is re-scaling gradient updates by class frequency more effective than class-weighting in cross-entropy?
ML Interview Series

ML Interview Q Series: Why is re-scaling…

Rohan Paul
Mar 28
1

Share this post

Rohan's Bytes
Rohan's Bytes
ML Interview Q Series: Why is re-scaling gradient updates by class frequency more effective than class-weighting in cross-entropy?

πŸ“š Browse the full ML Interview series here.

Read β†’
Comments
User's avatar
Β© 2025 Rohan Paul
Privacy βˆ™ Terms βˆ™ Collection notice
Start writingGet the app
Substack is the home for great culture

Share