Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees

02/08/2023
by   Marco Bressan, et al.
0

We give the first algorithm that maintains an approximate decision tree over an arbitrary sequence of insertions and deletions of labeled examples, with strong guarantees on the worst-case running time per update request. For instance, we show how to maintain a decision tree where every vertex has Gini gain within an additive α of the optimum by performing O(d (log n)^4/α^3) elementary operations per update, where d is the number of features and n the maximum size of the active set (the net result of the update requests). We give similar bounds for the information gain and the variance gain. In fact, all these bounds are corollaries of a more general result, stated in terms of decision rules – functions that, given a set S of labeled examples, decide whether to split S or predict a label. Decision rules give a unified view of greedy decision tree algorithms regardless of the example and label domains, and lead to a general notion of ϵ-approximate decision trees that, for natural decision rules such as those used by ID3 or C4.5, implies the gain approximation guarantees above. The heart of our work provides a deterministic algorithm that, given any decision rule and any ϵ > 0, maintains an ϵ-approximate tree using O(d f(n)/npolyh/ϵ) operations per update, where f(n) is the complexity of evaluating the rule over a set of n examples and h is the maximum height of the maintained tree.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/01/2022

Fully-Dynamic Decision Trees

We develop the first fully dynamic algorithm that maintains a decision t...
research
11/19/2020

Fully Dynamic Approximation of LIS in Polylogarithmic Time

We revisit the problem of maintaining the longest increasing subsequence...
research
05/08/2021

Learning stochastic decision trees

We give a quasipolynomial-time algorithm for learning stochastic decisio...
research
09/04/2018

Maximizing net income of the auction waterfall with an abort decision tree

An online auction waterfall for an ad impression may contain auctions th...
research
12/31/2022

Power of Decision Trees with Monotone Queries

In this paper, we initiate study of the computational power of adaptive ...
research
06/18/2017

Data set operations to hide decision tree rules

This paper focuses on preserving the privacy of sensitive patterns when ...
research
08/02/2020

Interpretable Rule Discovery Through Bilevel Optimization of Split-Rules of Nonlinear Decision Trees for Classification Problems

For supervised classification problems involving design, control, other ...

Please sign up or login with your details

Forgot password? Click here to reset