dShrink is a model-free transfer estimator using summary statistics that is guaranteed to have lower expected quadratic error than the target-only estimator under arbitrary population heterogeneity.
Learning from similar linear representations: Adaptivity, minimaxity, and robustness
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
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 nonparametric model-agnostic framework purifies noisy labels with a small clean dataset for robust classification under label noise.
citing papers explorer
-
Divide-and-shrink: An efficient and heterogeneity-agnostic approach for transfer estimation using summary statistics
dShrink is a model-free transfer estimator using summary statistics that is guaranteed to have lower expected quadratic error than the target-only estimator under arbitrary population heterogeneity.
-
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.
-
Model-agnostic information transfer and fusion for classification with label noise
A nonparametric model-agnostic framework purifies noisy labels with a small clean dataset for robust classification under label noise.