Yahya Alkhatib
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Risk-Aware Output Control Should be the Focus of Machine Unlearning
According to the abstract, Alkhatib, Xiao and Tay argue in a position paper that machine unlearning should aim at statistically guaranteed control of model outputs rather than closeness to a model retrained from scratch, citing empirical and recent theoretical support.