Travelled to:1 × China
1 × France
Collaborated with:J.Sohl-Dickstein B.Poole E.A.Weiss N.Maheswaranathan
Talks about:nonequilibrium (1) thermodynam (1) unsupervis (1) stochast (1) gradient (1) newton (1) method (1) unifi (1) scale (1) quasi (1)
Person: Surya Ganguli
DBLP: Ganguli:Surya
Contributed to:
20152014Wrote 2 papers:
- ICML-2015-Sohl-DicksteinW #learning #using
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics (JSD, EAW, NM, SG), pp. 2256–2265.
- ICML-c2-2014-Sohl-DicksteinPG #optimisation #performance #probability #scalability
- Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods (JSD, BP, SG), pp. 604–612.