`Travelled to:`

1 × Canada

1 × China

1 × Finland

1 × Germany

1 × United Kingdom

4 × USA

`Collaborated with:`

A.J.Smola T.Mikolov T.Sarlós C.B.Do C.Foo T.Gärtner S.Canu A.Y.Ng N.Quadrianto T.S.Caetano C.H.Teo S.V.N.Vishwanathan J.Ngiam A.Coates A.Lahiri B.Prochnow M.Ranzato R.Monga M.Devin G.Corrado K.Chen J.Dean

`Talks about:`

learn (3) regular (2) label (2) heteroscedast (1) unsupervis (1) represent (1) loglinear (1) distribut (1) knowledg (1) gaussian (1)

## Person: Quoc V. Le

### DBLP: Le:Quoc_V=

### Contributed to:

### Wrote 9 papers:

- ICML-c2-2014-LeM #distributed #documentation
- Distributed Representations of Sentences and Documents (QVL, TM), pp. 1188–1196.
- ICML-c3-2013-LeSS #named
- Fastfood — Computing Hilbert Space Expansions in loglinear time (QVL, TS, AJS), pp. 244–252.
- ICML-2012-LeRMDCCDN #learning #scalability #using
- Building high-level features using large scale unsupervised learning (QVL, MR, RM, MD, GC, KC, JD, AYN), p. 69.
- ICML-2011-LeNCLPN #learning #on the #optimisation
- On optimization methods for deep learning (QVL, JN, AC, AL, BP, AYN), pp. 265–272.
- ICML-2009-DoLF #learning #online
- Proximal regularization for online and batch learning (CBD, QVL, CSF), pp. 257–264.
- ICML-2008-QuadriantoSCL
- Estimating labels from label proportions (NQ, AJS, TSC, QVL), pp. 776–783.
- KDD-2007-TeoSVL #composition #scalability
- A scalable modular convex solver for regularized risk minimization (CHT, AJS, SVNV, QVL), pp. 727–736.
- ICML-2006-LeSG #knowledge-based
- Simpler knowledge-based support vector machines (QVL, AJS, TG), pp. 521–528.
- ICML-2005-LeSC #process
- Heteroscedastic Gaussian process regression (QVL, AJS, SC), pp. 489–496.