Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Browse files

Added new notes section

  • Loading branch information...
commit b71dc936ad422157e6b91840be7316048f62f71a 1 parent f59b56f
Mark Reid authored
View
12 _includes/nav-note.html
@@ -0,0 +1,12 @@
+<h1>
+ <a href="/work/note/" title="">Notes</a>
+ <span class="byline">&larr; <a href="/work/">Research</a></span>
+ <span class="byline">&larr; <a href="/">Mark Reid</a></span>
+</h1>
+<ul class="nav">
+ <li><a class="home" href="/">Home</a></li>
+ <li><a class="info" href="/info">Info</a></li>
+ <li><a class="work" href="/work">Work</a></li>
+ <li><a class="code" href="/code">Code</a></li>
+</ul>
+
View
2  _includes/nav-sap.html
@@ -1,4 +1,4 @@
<h1>
- <a href="/sap/" title="A machine learning blog">Structure <i>&amp;</i> Process</a>
+ <a href="/sap/" title="A programming blog">Structure <i>&amp;</i> Process</a>
<span class="byline">&larr; <a href="/">Mark Reid</a></span>
</h1>
View
27 _layouts/note.html
@@ -0,0 +1,27 @@
+---
+layout: default
+top: Notes &larr; Mark Reid
+section: Work
+feed: atom.xml
+---
+
+<div id="header">
+ {% include nav-note.html %}
+</div>
+
+<div id="page">
+
+ <h1 class="emphnext">{{ page.title }}</h1>
+
+{{ content }}
+
+ <address class="signature">
+ <a class="author" href="http://mark.reid.name">Mark Reid</a>
+ <span class="date">
+ {{ page.date | date_to_long_string }}
+ {% if page.update %}
+ &#8212; {{ page.update | date_to_long_string }}
+ {% endif %}
+ </span>
+ </address>
+</div><!-- End Page -->
View
22 work/note/online-learning.md
@@ -0,0 +1,22 @@
+---
+title: Online Learning
+layout: note
+
+date: 2009-07-17
+---
+Online learning is a modern take on the early perceptron work that uses gradient descent methods to update models as training example are examined sequentially.
+
+References
+----------
+
+* J. Abernethy, A. Agarwal, P. L. Bartlett, and A. Rakhlin, _[A Stochastic View of Optimal Regret through Minimax Duality](http://arxiv.org/abs/0903.5328)_ (2009).
+
+* S. Shalev-Shwartz, O. Shamir, N. Srebro, and K. Sridharan, _[Stochastic Convex Optimization](http://eprints.pascal-network.org/archive/00005408/01/2009_COLT_ShalShamSreSri.pdf)_ (2009).
+
+* M. Raginsky, R. Marcia, J. Silva, and R. Willett, _[Sequential probability assignment via online convex programming using exponential families](http://people.ee.duke.edu/~maxim/pubs/raginsky_marcia_silva_willett_ISIT09.pdf)_ (2009).
+
+* P. L. Bartlett, E. Hazan, and A. Rakhlin, _[Adaptive Online Gradient Descent](http://dblp.uni-trier.de/rec/bibtex/conf/nips/BartlettHR07)_ (2007).
+
+* N. Cesa-Bianchi and G. Lugosi, _[Prediction, Learning, and Games](http://books.google.com/books?id=zDnRBlazhfYC&dq=Prediction+Learning+and+games&printsec=frontcover&source=bn&hl=en&ei=BQxgSt-eJqCQ6APL85WXCw&sa=X&oi=book_result&ct=result&resnum=4)_ (2006).
+
+{:.compact .quiet }
Please sign in to comment.
Something went wrong with that request. Please try again.