• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Daria Musatkina
Empirical Study of Deep Neural Network Loss Surfaces
9
2019
The loss functions of deep neural networks are complex and their geometric prop- erties are not well understood. In recent papers it has been empirically shown that neural network loss minima found with stochastic gradient descent form a connected manifold. In this work, we research loss function behavior along a path that connects optima with low gradient norm and connectivity of overfitted minima and minima with good generalization. The results show that optima with lower gradient norm are not connected with simple curve but the increase in loss is not big. Also optima with dif- ferent generalization ability of the specific network architecture are not connected.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses