Soumik Mandal

Publications4
h-index3
Citations1,080
Highly Influential Citations123
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Mikhail Belkin
  • 134 Publications • 25,031 Citations
  • Siyuan Ma
  • 19 Publications • 1,589 Citations
  • Nathan Srebro
  • 201 Publications • 21,818 Citations
  • L. Rosasco
  • 248 Publications • 8,529 Citations
  • Publications
  • Influence
Reconciling modern machine-learning practice and the classical bias–variance trade-off
TLDR
This work shows how classical theory and modern practice can be reconciled within a single unified performance curve and proposes a mechanism underlying its emergence, and provides evidence for the existence and ubiquity of double descent for a wide spectrum of models and datasets.
View on Publisher
To understand deep learning we need to understand kernel learning
TLDR
It is argued that progress on understanding deep learning will be difficult until more tractable "shallow" kernel methods are better understood, and a need for new theoretical ideas for understanding properties of classical kernel methods.
View PDF on arXiv
Reconciling modern machine learning and the bias-variance trade-off
TLDR
A new "double descent" risk curve is exhibited that extends the traditional U-shaped bias-variance curve beyond the point of interpolation and shows that the risk of suitably chosen interpolating predictors from these models can, in fact, be decreasing as the model complexity increases, often below the risk achieved using non-interpolating models.
Reply to Loog et al.: Looking beyond the peaking phenomenon
The letter “A brief prehistory of double descent” (1) written in response to our article “Reconciling modern machine-learning practice and the classical bias–variance trade-off” (2) brings a number…
View on Publisher