New answers tagged lg.learning
2
I'm not sure if this is what you're looking for, but people have studied consistency of surrogate risk minimization. There, we define a surrogate loss function $L$ and a link $\psi$. We first minimize surrogate loss on our dataset, yielding some surrogate hypothesis $h$. Then we define $f(x) = \psi(h(x))$. This procedure is roughly consistent if, as data $\...
Top 50 recent answers are included
Related Tags
lg.learning × 179machine-learning × 110
reference-request × 36
vc-dimension × 23
pac-learning × 20
cc.complexity-theory × 17
boolean-functions × 17
st.statistics × 16
cg.comp-geom × 10
online-learning × 10
ds.algorithms × 9
sample-complexity × 8
pr.probability × 7
query-complexity × 6
automata-theory × 5
clustering × 5
fourier-analysis × 4
optimization × 3
computability × 3
circuit-complexity × 3
cr.crypto-security × 3
dfa × 3
ne.neural-evol × 3
online-algorithms × 3
graph-theory × 2