Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Colin Sandon

Colin Sandon

Spectral Algorithms Optimally Recover (Censored) Planted Dense Subgraphs

Mar 22, 2022
Souvik Dhara, Julia Gaudio, Elchanan Mossel, Colin Sandon

Figure 1 for Spectral Algorithms Optimally Recover (Censored) Planted Dense Subgraphs

Figure 2 for Spectral Algorithms Optimally Recover (Censored) Planted Dense Subgraphs

* 24 pages, 2 figures

Access Paper or Ask Questions

On the Power of Differentiable Learning versus PAC and SQ Learning

Aug 09, 2021
Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro

Figure 1 for On the Power of Differentiable Learning versus PAC and SQ Learning

Access Paper or Ask Questions

Spoofing Generalization: When Can't You Trust Proprietary Models?

Jun 15, 2021
Ankur Moitra, Elchanan Mossel, Colin Sandon

Access Paper or Ask Questions

Learning to Sample from Censored Markov Random Fields

Jan 15, 2021
Ankur Moitra, Elchanan Mossel, Colin Sandon

Access Paper or Ask Questions

Poly-time universality and limitations of deep learning

Jan 07, 2020
Emmanuel Abbe, Colin Sandon

Figure 1 for Poly-time universality and limitations of deep learning

Figure 2 for Poly-time universality and limitations of deep learning

Figure 3 for Poly-time universality and limitations of deep learning

Figure 4 for Poly-time universality and limitations of deep learning

* arXiv admin note: substantial text overlap with arXiv:1812.06369

Access Paper or Ask Questions

Provable limitations of deep learning

Dec 16, 2018
Emmanuel Abbe, Colin Sandon

Figure 1 for Provable limitations of deep learning

Figure 2 for Provable limitations of deep learning

Access Paper or Ask Questions

Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap

Sep 15, 2016
Emmanuel Abbe, Colin Sandon

Figure 1 for Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap

Figure 2 for Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap

* Extended version with further details on the algorithms and methods

Access Paper or Ask Questions

Recovering communities in the general stochastic block model without knowing the parameters

Jun 11, 2015
Emmanuel Abbe, Colin Sandon

Figure 1 for Recovering communities in the general stochastic block model without knowing the parameters

* arXiv admin note: substantial text overlap with arXiv:1503.00609

Access Paper or Ask Questions