pith. sign in

Algorithmic Transparency via Quantitative Input Influence :

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2019 2

verdicts

UNVERDICTED 2

representative citing papers

The Price of Interpretability

cs.LG · 2019-07-08 · unverdicted · novelty 6.0

Introduces a framework for constructing ML models via interpretable steps, generalizes standard proxies into a parametrized family of measures, and quantifies the accuracy-interpretability tradeoff via practical algorithms.

Optimal Explanations of Linear Models

cs.LG · 2019-07-08 · unverdicted · novelty 5.0

An optimization framework decomposes linear models into increasing-complexity sequences using coordinate updates to generate parametrized interpretability metrics.

citing papers explorer

Showing 2 of 2 citing papers.

  • The Price of Interpretability cs.LG · 2019-07-08 · unverdicted · none · ref 11

    Introduces a framework for constructing ML models via interpretable steps, generalizes standard proxies into a parametrized family of measures, and quantifies the accuracy-interpretability tradeoff via practical algorithms.

  • Optimal Explanations of Linear Models cs.LG · 2019-07-08 · unverdicted · none · ref 16

    An optimization framework decomposes linear models into increasing-complexity sequences using coordinate updates to generate parametrized interpretability metrics.