Sejun Park

activity

20172026

most citedLookahead: A Far-Sighted Alternative of Magnitude-based Pruning

17 citations · 41 across the 14 of their papers we have counts for

collaborators

Showing 2022 · stat.MLShow all

2 papers · 2 filters

stat.ML2022★ 1 cited

Generalization Bounds for Stochastic Gradient Descent via Localized $ε$ -Covers

Sejun Park, Umut Şimşekli, Murat A. Erdogdu

In this paper, we propose a new covering technique localized for the trajectories of SGD. This localization provides an algorithm-specific complexity measured by the covering numbe…

stat.ML2022★ 6 cited

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti +2

We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $x \in R^{d}$ is Gaus…

Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

Generalization Bounds for Stochastic Gradient Descent via Localized $ε$ -Covers