For binary classification, the optimal tradeoff curve between stored bits and class information is achieved by binning the posterior class probability into contiguous intervals.
Thermodynamic cost and benefit of memory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This letter exposes a tight connection between the thermodynamic efficiency of information processing and predictive inference. A generalized lower bound on dissipation is derived for partially observable information engines which are allowed to use temperature differences. It is shown that the retention of irrelevant information limits efficiency. A data representation strategy is derived from optimizing a fundamental physical limit to information processing: minimizing the lower bound on dissipation leads to a data compression method that maximally retains relevant, predictive, information. In that sense, predictive inference emerges as the strategy that least precludes energy efficiency.
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.