AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Learning the Behavior of a Dynamical System Via a “20 Questions” Approach

Abhijin Adiga, Chris Kuhlman, Madhav Marathe, Ravi S. S., Daniel Rosenkrantz, Richard Stearns

AAAI 2018 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of MDPs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase number of random queries per degree class from l=2 to l=10Method 2 randomized query sets · 50 sampled sets per networknumber of complete query sets out of 50: 0 -> 5 to 50 complete setsImproved
apply compaction algorithm to randomized complete setsMethod 2 · real-world networksquery set size: 80% reductionImproved
apply compaction algorithm to coloring-based setsMethod 1 · real-world networksquery set sizeNo clear effect
use randomized plus compaction instead of G2 coloringMethod 2 vs Method 1 · real-world networksquery set size: 1.5 to 2 times that of Method 1Hurt
use adaptive greedy instead of batch coloringMethod 3 vs Method 1 · FBquery set size: 225 -> 53Improved
use adaptive greedy instead of batch coloringMethod 3 vs Method 1 · Enronquery set size: 1385 -> 624Improved
use adaptive greedy instead of batch coloringMethod 3 vs Method 1 · Cliquequery set size: 1001 -> 8Improved
widen threshold range theta from 0 to 1Method 3 · random k-regular graphsnumber of queriesHurt
widen threshold range thetaMethod 3 · real-world networksnumber of queries: less than 1.5ΔHurt
set uniform fixed threshold near Δ/2 versus near 0 or ΔMethod 3 · random k-regular graphsnumber of queries: maximum around Δ/2Mixed
increase graph degree kMethod 3 · random k-regular graphsnumber of queriesHurt
increase graph density with limited threshold rangeMethod 3 · dense networksnumber of queriesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy