research
∙
04/25/2023
SAFE: Machine Unlearning With Shard Graphs
We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt l...
share
research
∙
02/15/2023
À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
We introduce À-la-carte Prompt Tuning (APT), a transformer-based scheme ...
research
∙
11/15/2022
Characterizing the Spectrum of the NTK via a Power Series Expansion
Under mild conditions on the network initialization we derive a power se...
research
∙
06/06/2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
We provide quantitative bounds measuring the L^2 difference in function ...
research
∙
01/12/2022
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks
We study the dynamics of a neural network in function space when optimiz...
research
∙
08/20/2020