activity
20142024
most citedThe Loss Surfaces of Multilayer Networks

715 citations · 753 across the 7 of their papers we have counts for

collaborators

6 papers

cs.LG20211 cited

AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop

Yunfei Teng, Jing Wang, Anna Choromanska

Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a defined learning rate schedule, i.e., the learning ra…

cs.CR2021

ESAFE: Enterprise Security and Forensics at Scale

Bernard McShea, Kevin Wright, Denley Lam +7

Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffuse…

stat.ML201614 cited

Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation

Yacine Jernite, Anna Choromanska, David Sontag

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive po…

cs.LG2015715 cited

The Loss Surfaces of Multilayer Networks

Anna Choromanska, Mikael Henaff, Michael Mathieu +2

We study the connection between the highly non-convex loss function of a simple model of the fully-connected feed-forward neural network and the Hamiltonian of the spherical spin-g…

cs.LG20144 cited

Notes on using Determinantal Point Processes for Clustering with Applications to Text Clustering

Apoorv Agarwal, Anna Choromanska, Krzysztof Choromanski

In this paper, we compare three initialization schemes for the KMEANS clustering algorithm: 1) random initialization (KMEANSRAND), 2) KMEANS++, and 3) KMEANSD++. Both KMEANSRAND an…

cs.LG201418 cited

Differentially- and non-differentially-private random decision trees

Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski +1

We consider supervised learning with random decision trees, where the tree construction is completely random. The method is popularly used and works well in practice despite the si…