recitation 10

(no title)

Sat, 06 Jul 2019 17:18:31 +0000

but if alpha is positive but smaller than 1, wouldnt the integral diverge?

Re: recitation 10

Sat, 06 Jul 2019 15:24:31 +0000

Thanks Dan.
equation 22- it's not required to assume that alpha>1.

(no title)

Sat, 06 Jul 2019 06:56:37 +0000

thanks dan

(no title)

Fri, 05 Jul 2019 16:17:04 +0000

regarding equation 8 - I think the usage in Hoeffding's inequality should be:

(1)

\begin{align} exp( \frac{-2 \epsilon ^2 m^2}{\sum ^m _{i=1} (b_i - a_i)^2} )=exp( \frac{-2 \epsilon ^2 m^2}{\sum ^m _{i=1} (1 - 0)^2} )=exp( \frac{-2 \epsilon ^2 m^2}{m}) \end{align}

where $$m=T_i$$ because we get the mean $\hat \mu _{i,T_i}$ on $$T_i$$ samples

recitation 10

Fri, 05 Jul 2019 12:30:10 +0000

Shalom Lee,

In equation 8, shouldn't we write t instead of t square? indeed, in the last expression, the t square is replaced by t.

in the explanation before (16), delta(i) = mu1 - mu2

in equation 22, should we assume alpha is greather than 1?

Toda,
Rafi