Provably efficient, succinct, and precise explanations

11/01/2021
by   Guy Blanc, et al.
0

We consider the problem of explaining the predictions of an arbitrary blackbox model f: given query access to f and an instance x, output a small set of x's features that in conjunction essentially determines f(x). We design an efficient algorithm with provable guarantees on the succinctness and precision of the explanations that it returns. Prior algorithms were either efficient but lacked such guarantees, or achieved such guarantees but were inefficient. We obtain our algorithm via a connection to the problem of implicitly learning decision trees. The implicit nature of this learning task allows for efficient algorithms even when the complexity of f necessitates an intractably large surrogate decision tree. We solve the implicit learning problem by bringing together techniques from learning theory, local computation algorithms, and complexity theory. Our approach of "explaining by implicit learning" shares elements of two previously disparate methods for post-hoc explanations, global and local explanations, and we make the case that it enjoys advantages of both.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2022

Explaining Neural Networks without Access to Training Data

We consider generating explanations for neural networks in cases where t...
research
12/16/2020

Testing and reconstruction via decision trees

We study sublinear and local computation algorithms for decision trees, ...
research
05/19/2022

Provably Precise, Succinct and Efficient Explanations for Decision Trees

Decision trees (DTs) embody interpretable classifiers. DTs have been adv...
research
06/30/2022

On Computing Probabilistic Explanations for Decision Trees

Formal XAI (explainable AI) is a growing area that focuses on computing ...
research
07/13/2018

Model Reconstruction from Model Explanations

We show through theory and experiment that gradient-based explanations o...
research
11/21/2022

Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)

Random forests are decision tree ensembles that can be used to solve a v...
research
07/15/2013

The Fundamental Learning Problem that Genetic Algorithms with Uniform Crossover Solve Efficiently and Repeatedly As Evolution Proceeds

This paper establishes theoretical bonafides for implicit concurrent mul...

Please sign up or login with your details

Forgot password? Click here to reset