pith. sign in

arxiv: 1904.03866 · v1 · pith:32YMINR5new · submitted 2019-04-08 · 💻 cs.LG · stat.ML

On the Learnability of Deep Random Networks

Abhimanyu Das , Sreenivas Gollapudi , Ravi Kumar , Rina Panigrahy This is my paper
classification 💻 cs.LG stat.ML
keywords learnabilitydeepnetworksrandomtheoreticaldepthdropsfront
0
0 comments X
read the original abstract

In this paper we study the learnability of deep random networks from both theoretical and practical points of view. On the theoretical front, we show that the learnability of random deep networks with sign activation drops exponentially with its depth. On the practical front, we find that the learnability drops sharply with depth even with the state-of-the-art training methods, suggesting that our stylized theoretical results are closer to reality.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently

    cs.LG 2026-05 unverdicted novelty 7.0

    Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.