← Search

Manuela Girotti

2 accepted papers

2023

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

ICLR 2023top-25%

We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\boldsymbol{x}\in \mathbb{R}^d$ is Gaussian and the target $y \in \mathbb{R}$ follows a multiple-index model, i.e., $y=g(\langle\boldsymbol{u_1},\boldsymbol{x}…

Cited by 71SourcePDFScholar
2021

A Study of Condition Numbers for First-Order Optimization

AISTATS 2021poster

In this work we introduce a new framework for the theoretical study of convergence and tuning of first-order optimization algorithms (FOA). The study of such algorithms typically requires assumptions on the objective functions: the most popular ones are probably smoothness and strong convexity. Thes…

Cited by 24SourcePDFScholar