Statistical Learning
Rotating Features for Object Discovery
In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations.
OptimalRatesforVector-ValuedSpectral RegularizationLearningAlgorithms
We study theoretical properties of a broad class of regularized algorithms with vector-valued output.
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training Y anlai Y ang 1, Matt Jones
The behavior emerges and becomes more robust as the architecture scales up its number of parameters.
Adapting Fairness Interventions to Missing Values
Missing values in real-world data pose a significant and unique challenge to algorithmic fairness.
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
Technically, our result is enabled by establishing a link with recent works on optimal denoising of extensive-rank matrices and on the ellipsoid fitting problem.
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
This illustrates the dependence of the classifier on the representation's robustness, i.e., the predictor can only be robust if