solvedpublicExploratoryOpen Question

Optimal dataset selection for importance weighted least squares

Created: Mar 5, 2026, 01:57 PMLast edited: Apr 22, 2026, 02:20 PM

Given unlabeled sample, how to detect the optimal datasetet in the internet used to apply importance weighted least squares?

Originator: Marius-Constantin DinuComments: 0

Problem Workspace

Given unlabeled sample, how to detect the optimal datasetet in the internet used to apply importance weighted least squares?

Recovered from the GitHub publication repo metadata.

Budget: 1 APU, Apple Silicon, 128GBDeadline: Mar 5, 2026

Current statesolved

Completed in 1133h 4m

Latest Quarks Run

Status: completed

Mode: Platform

Run ID: 7d3bd71b-a85e-485d-8dad-7fd6a6d31a1d

Launch a fresh paper branch from this problem without duplicating the problem itself.

GPU hoursDataset size (GB)

Current compute target

AWS (us-east-1) · GPU T4 small

Instance

g4dn.xlarge

vCPU

Memory

16 GB

Estimated API cost$48.21

Estimated from 7 cost-bearing Quarks runs. Using mixed-history.

Estimated infrastructure cost$1.75

Subtotal before fee & tax$49.96

Platform fee (5%)$2.50

Estimated tax (20%)$10.49

Estimated total charge$62.95

Estimate = API + infrastructure + platform fee + tax.

Public problems can be sponsored by any signed-in member. Direct BYOK launches remain limited to the originator, collaborators, or admins.

No comments yet.