Random Projections, Margins and Learning

Speaker: 

Time: 

Friday, 8 March 2013, 14:30 to 16:00

Venue: 

Organisers: 

In this talk we will give an introduction to random projections. Define the linear separability of data by a margin $\gamma$. Then we will see a simple algorithm to learn a linear separator and show that it will have error at most $\frac{1}{2} - \frac{\gamma}{4}$ with probability $\Omega(\gamma)$.