For binary classification, the optimal tradeoff curve between stored bits and class information is achieved by binning the posterior class probability into contiguous intervals.
For practical exam- ples where this is not the case, we can instead train a neural network to implement a function ˆw(X) that ap- proximatesP (Y =1|X)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pareto-optimal data compression for binary classification tasks
For binary classification, the optimal tradeoff curve between stored bits and class information is achieved by binning the posterior class probability into contiguous intervals.