AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Fundamental Tradeoffs in Learning with Prior Information

Anirudha Majumdar

ICML 2023 · Learning theory and algorithms › Sample complexity · approach: Generalization and limits under data constraints · 0 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
Weight risk by the learner's prior and use the resulting prioritized-risk frameworkLearning problems where reality may not conform to the learner's prior · General learning problemsprioritized risk lower boundImproved
Reduce estimation to testing with a prior-weighted test and a (δ, π)-packingEstimation problems · General estimation problemsprioritized risk lower boundImproved
Apply the generalized Fano inequality using the Donsker–Varadhan change-of-measure inequalityGeneral learning problems with unbounded losses · General learning problemsBayes risk lower boundImproved
Use a more concentrated Beta(α=1, β=4) priorBayesian inference for Bernoulli mean estimation · Bernoulli mean estimationlearner-specific prioritized riskImproved
Use regressors with smaller L2 normLogistic regression with directional priors · Logistic regressionprioritized risk lower boundImproved
Restrict the available policy set from 50 policies to 5RL agent in Zipfian Gridworld environments · Zipfian Gridworld environmentsprioritized risk lower boundHurt

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