paper-with-me

홈 › Papers

A Note on Connectivity of Sublevel Sets in Deep Learning

2021-01-21 · Quynh Nguyen

It is shown that for deep neural networks, a single wide layer of width $N+1$ ($N$ being the number of training samples) suffices to prove the connectivity of sublevel sets of the training loss function. In the two-layer setting, the same property may not hold even if one has just one neuron less (i.e. width $N$ can lead to disconnected sublevel sets).

📄 PDF Abstract BibTeX arXiv:2101.08576

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

From Approximation Rates to Loss-Landscape Barrier Decay in Shallow ReLU Networks

2026-02-19 · Saveliy Baturin arxiv

We study pathwise connectivity of sublevel sets for one-hidden-layer ReLU networks with constrained first-layer weights and an $\ell_1$ penalty on the output layer. The data term is assumed convex and globally Lipschitz …

On Connected Sublevel Sets in Deep Learning

2019-01-22 · Quynh Nguyen

This paper shows that every sublevel set of the loss function of a class of deep over-parameterized neural nets with piecewise linear activation functions is connected and unbounded. This implies that the loss has no bad…

Deep Learning

When Are Solutions Connected in Deep Networks?

2021-02-18 · NeurIPS 2021 12 · Quynh Nguyen, Pierre Brechet, Marco Mondelli

The question of how and why the phenomenon of mode connectivity occurs in training deep neural networks has gained remarkable attention in the research community. From a theoretical perspective, two possible explanations…

Guarantees for Hierarchical Clustering by the Sublevel Set method

2020-06-18 · Marina Meila

Meila (2018) introduces an optimization based method called the Sublevel Set method, to guarantee that a clustering is nearly optimal and "approximately correct" without relying on any assumptions about the distribution …

Clustering

Robust Control Barrier Functions under High Relative Degree and Input Constraints for Satellite Trajectories

2021-07-08 · Joseph Breeden, Dimitra Panagou

This paper presents methodologies for constructing Control Barrier Functions (CBFs) for nonlinear, control-affine systems, in the presence of input constraints and bounded disturbances. More specifically, given a constra…