Pith. sign in

Learning topic models - going beyond svd, 2012 b

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Provable unlearning in topic modeling and downstream tasks

cs.LG · 2024-11-19 · conditional · novelty 7.0

Provable (epsilon, delta)-unlearning algorithms for topic models achieve deletion capacity O~(m/(r^2 sqrt(nr))) before fine-tuning and O~(m q/(r sqrt(nr))) after fine-tuning, with the base model untouched in the downstream case.

citing papers explorer

Showing 1 of 1 citing paper.

  • Provable unlearning in topic modeling and downstream tasks cs.LG · 2024-11-19 · conditional · none · ref 3

    Provable (epsilon, delta)-unlearning algorithms for topic models achieve deletion capacity O~(m/(r^2 sqrt(nr))) before fine-tuning and O~(m q/(r sqrt(nr))) after fine-tuning, with the base model untouched in the downstream case.