leon.bottou.org

User Tools

Site Tools

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
papers:bottou-lecun-2004 [2006/04/18 17:47]
leonb 		papers:bottou-lecun-2004 [2018/12/06 10:00] (current)
leonb
Line 9: Line 9:
  
 <box 99% orange> <box 99% orange>
-Léon Bottou and Yann LeCun: Large Scale Online Learning,  //Advances in Neural Information Processing Systems 16//, Edited by Sebastian Thrun, Lawrence Saul and Bernhard Schölkopf, MIT Press, Cambridge, MA, 2004.+Léon Bottou and Yann LeCun: **Large Scale Online Learning**,  //Advances in Neural Information Processing Systems 16  
 + 
 +(NIPS 2003)//, Edited by Sebastian Thrun, Lawrence Saul and Bernhard Schölkopf, MIT Press, Cambridge, MA, 2004.
  
 [[http://leon.bottou.org/publications/djvu/nips-2003.djvu|nips-2003.djvu]] [[http://leon.bottou.org/publications/djvu/nips-2003.djvu|nips-2003.djvu]]
Line 16: Line 18:
 </box> </box>
  
-  @inproceedings{bottou-lecun-2004,+  @incollection{bottou-lecun-2004,
     author = {Bottou, L\'{e}on and {LeCun}, Yann},     author = {Bottou, L\'{e}on and {LeCun}, Yann},
     title = {Large Scale Online Learning},     title = {Large Scale Online Learning},
-    booktitle = {Advances in Neural Information Processing Systems 16},+    booktitle = {Advances in Neural Information Processing Systems 16 (NIPS 2003)},
     editor = {Thrun, Sebastian and Saul, Lawrence and Bernhard {Sch\"{o}lkopf}},     editor = {Thrun, Sebastian and Saul, Lawrence and Bernhard {Sch\"{o}lkopf}},
     publisher = {MIT Press},     publisher = {MIT Press},
Line 29: Line 31:
 ==== Notes ==== ==== Notes ====
  
-Complete proofs can be found in [[bottou-lecun-2004a|(Bottou and LeCun, 2004a)]].+The ASMB version of this work [[bottou-lecun-2004a|(Bottou and LeCun, 2005)]] contains the complete proof. The NIPS version was written several months after the ASMB. It contains only a proof sketch but reports experimental results. It also offers a better discussion of the previous results obtained by Murata and Amari (1998) which are in fact much more general than I initially realized. Relative to these results, this work contains three contributions: (a) spelling out the computational consequences of the efficiency results, (b) expressing the solution of the batch learning problems as a stochastic process that is fundamentally similar to a second order stochastic gradient algorithm, and (<html></html>c) providing a more rigorous proof, taking into account, for instance, how the gain matrix approximates the inverse Hessian. 
 + 
 +  
papers/bottou-lecun-2004.1145396864.txt.gz · Last modified: 2006/04/20 11:02 (external edit)

Page Tools