Learning Narrow One-Hidden-Layer ReLU Networks

April 20, 2023 ยท Declared Dead ยท ๐Ÿ› Annual Conference Computational Learning Theory

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Sitan Chen, Zehao Dou, Surbhi Goel, Adam R Klivans, Raghu Meka arXiv ID 2304.10524 Category cs.LG: Machine Learning Cross-listed cs.DS, stat.ML Citations 17 Venue Annual Conference Computational Learning Theory Last Checked 3 months ago
Abstract
We consider the well-studied problem of learning a linear combination of $k$ ReLU activations with respect to a Gaussian distribution on inputs in $d$ dimensions. We give the first polynomial-time algorithm that succeeds whenever $k$ is a constant. All prior polynomial-time learners require additional assumptions on the network, such as positive combining coefficients or the matrix of hidden weight vectors being well-conditioned. Our approach is based on analyzing random contractions of higher-order moment tensors. We use a multi-scale analysis to argue that sufficiently close neurons can be collapsed together, sidestepping the conditioning issues present in prior work. This allows us to design an iterative procedure to discover individual neurons.
Community shame:
Not yet rated
Community Contributions

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

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted