4 papers
ARO: A New Lens On Matrix Optimization For Large Models
Wenbo Gong, Javier Zazo, Qijun Luo +3
Matrix-based optimizers have attracted growing interest for improving LLM training efficiency, with significant progress centered on orthogonalization/whitening based methods. Whil…
Robustly Learning Monotone Single-Index Models
Puqian Wang, Nikos Zarifis, Ilias Diakonikolas +1
We consider the basic problem of learning Single-Index Models with respect to the square loss under the Gaussian distribution in the presence of adversarial label noise. Our main c…
Robustly Learning Monotone Generalized Linear Models via Data Augmentation
Nikos Zarifis, Puqian Wang, Ilias Diakonikolas +1
We study the task of learning Generalized Linear models (GLMs) in the agnostic model under the Gaussian distribution. We give the first polynomial-time algorithm that achieves a co…
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
Puqian Wang, Nikos Zarifis, Ilias Diakonikolas +1
A single-index model (SIM) is a function of the form , where is a known link function and $\mathbf{w}^{\ast}…