Probe evasion training might also work best for polynomial probes because polynomial probes are linearly dependent, so the network only needs to be able to evade finitely many probes. The linear dependence of polynomials is probably why it is easier to evade polynomial probes.
Probe evasion training might also work best for polynomial probes because polynomial probes are linearly dependent, so the network only needs to be able to evade finitely many probes. The linear dependence of polynomials is probably why it is easier to evade polynomial probes.