AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Neural Pseudo-Label Optimism for the Bank Loan Problem

Aldo Pacchiano, Shaun Singh, Edward Chou, Alexander C. Berg, Jakob Nicolaus Foerster

NeurIPS 2021 · Bandits and online learning › Online convex optimization and games · approach: Online decision-making with feedback structure · 1 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
train for XOR boundary: more batches seen (batch 1 to batch 81)PLOT · XOR toy datasettest accuracy (%): $50\%$ -> $97.8\%$Improved
more batches seen (batch 81 to batch 105)PLOT · XOR toy datasettest accuracy (%): $97.8\%$ -> $99.9\%$Improved
use optimistic pseudo-labels rather than NeuralUCB / greedy explorationneural bank loan learner · MNIST (digit 5 vs rest)cumulative regretImproved
PLOT versus NeuralUCB and Greedy on run-to-run variancePLOT · Adult, Bank, MNISTvariance of cumulative regretImproved
PLOT versus NeuralUCB / epsilon-greedy / greedy on Adult and BankPLOT · Adult, Bankcumulative regretNo clear effect
default PLOT weight 1 and radius infinity without tuningPLOT · Adult, Bank, MNISTcumulative regretNo clear effect
pseudo-label optimism instead of decayed epsilon-greedyPLOT · Adult, Bank, MNISTprobability of accepting positives vs negatives: 3-5 timesImproved

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