# Is testing easier/harder than learning?

How is the Property testing is related to PAC model of learning?

More precisely,

Let we have given a property tester, $\mathcal{A}$, for the (concept) class of function $\mathcal{F_n}$ which receives as input a size parameter $n$ (labeled input $(x_1,f(x_1)), (x_2,f(x_2)),...,(x_n,f(x_n))$), distance parameter $0<\epsilon<1$, confidence interval $0<\delta<1/2$, and does the following:

-if $f\in \mathcal{F_n}$, then with probability probability $(1-\delta)$ (over the choice of $x_i$'s) $\mathcal{A}$ accepts $f$.

-if $f$ is $\epsilon$-far from $\mathcal{F_n}$, then with probability probability $(1-\delta)$ (over the choice of $x_i$'s) $\mathcal{A}$ rejects $f$.

Now, I have following two questions:

1) Now, how this tester $\mathcal{A}$ can be used to generate learning algorithm (under PAC learning model) for the concept class $\mathcal{F_n}$, and vice versa. And how does VC-dim of $\mathcal{F_n}$ plays role in the reduction.

2) Can we give some sort of characterization (for example, on the basis of VC-dim) over the concept class for which testing is easier/harder than learning?

Pls let me know if I am not able to put the question clearly.

Thanks.

-
The paper of Goldreich, Goldwasser, and Ron should help a lot: groups.csail.mit.edu/cis/pubs/shafi/1998-jacm.pdf. –  Sasho Nikolov Apr 20 '14 at 18:30
You can have a look at these lecture notes — they are quite short, and should answer your question. –  Clement C. Apr 21 '14 at 12:19

If the learning algorithm is proper (i.e. it always produces a hypothesis from the class $F_n$), then it also gives a testing algorithm -- simply run the learning algorithm, and see whether the hypothesis it produced has error rate $<\epsilon$, which can be done with only $\approx 1/\epsilon^2$ samples. If it does, since the hypothesis is in $F_n$, this is a constructive proof that the function you are testing has distance at most $\epsilon$ from $F_n$. If the algorithm was a PAC learning algorithm for $F_n$, then when $f \in F_n$, it must generate such a hypothesis. So any proper learning algorithm can be converted to a testing algorithm with only an additional $\approx 1/\epsilon^2$ samples at most.
Moreover, if you are only worried about sample complexity and not computational efficiency, then without loss of generality you can always use a proper PAC learning algorithm. Since the sample complexity of learning is $\mathrm{VCDIM}(F_n)/\epsilon^2$, this means you can always test with at most this many samples.
However, generally testing is easier than learning. For example, linear functions in $d$ dimensions require $d$ samples to learn, but only a constant number of samples to test.