Convergence Results for Neural Networks via Electrodynamics

February 01, 2017 Β· Declared Dead Β· πŸ› Information Technology Convergence and Services

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Rina Panigrahy, Sushant Sachdeva, Qiuyi Zhang arXiv ID 1702.00458 Category cs.DS: Data Structures & Algorithms Cross-listed cs.LG, physics.data-an Citations 22 Venue Information Technology Convergence and Services Last Checked 3 months ago
Abstract
We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient descent converges to the target function is equivalent to the following question in electrodynamics: Given $k$ fixed protons in $\mathbb{R}^d,$ and $k$ electrons, each moving due to the attractive force from the protons and repulsive force from the remaining electrons, whether at equilibrium all the electrons will be matched up with the protons, up to a permutation. Under the standard electrical force, this follows from the classic Earnshaw's theorem. In our setting, the force is determined by the activation function and the input distribution. Building on this equivalence, we prove the existence of an activation function such that gradient descent learns at least one of the hidden nodes in the target network. Iterating, we show that gradient descent can be used to learn the entire network one node at a time.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Data Structures & Algorithms

Died the same way β€” πŸ‘» Ghosted