AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

The power of absolute discounting: all-dimensional distribution estimation

Moein Falahatgar, Mesrob I Ohannessian, Alon Orlitsky, Venkatadheeraj Pichapati

NeurIPS 2017 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 6 citations (OpenAlex)

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
use absolute discounting instead of empirical, add-beta, Braess-Sauer, or Paninski estimatorsabsolute discounting estimator · synthetic power-law alpha=2, k=1000expected KL lossImproved
use absolute discounting on piece-wise power-law instead of pure power-lawabsolute discounting estimator · piece-wise power-law (1.3, 2, 1.5)expected KL lossNo clear effect
compare Good-Turing + empirical with absolute discountingGood-Turing + empirical · synthetic power-lawexpected KL lossNo clear effect
use absolute discounting vs frequency estimator for unseen low-activity citiesabsolute discounting estimator · START terrorism forecasting, low-activity citiesforecast of total incidentsImproved
use absolute discounting vs frequency estimator for medium-activity citiesabsolute discounting estimator · START terrorism forecasting, medium-activity citiesforecast of total incidentsImproved
use Braess-Sauer instead of absolute discounting for high-activity citiesBraess-Sauer estimator · START terrorism forecasting, high-activity citiesforecast accuracyHurt
increase n with fixed kabsolute discounting · power-law alpha=2, k in 100..3000expected KL lossImproved

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