Meta Subspace Pursuit learns the invariant low-rank subspace in multi-task linear models with provable algorithmic and statistical guarantees and outperforms baselines like ANIL in experiments.
A survey on multi-task learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Few-shot Multi-Task Learning of Linear Invariant Features with Meta Subspace Pursuit
Meta Subspace Pursuit learns the invariant low-rank subspace in multi-task linear models with provable algorithmic and statistical guarantees and outperforms baselines like ANIL in experiments.