paper-with-me

홈 › Papers

On the Benefit of Width for Neural Networks: Disappearance of Bad Basins

2018-12-28 · Dawei Li, Tian Ding, Ruoyu Sun

Wide networks are often believed to have a nice optimization landscape, but what rigorous results can we prove? To understand the benefit of width, it is important to identify the difference between wide and narrow networks. In this work, we prove that from narrow to wide networks, there is a phase transition from having sub-optimal basins to no sub-optimal basins. Specifically, we prove two results: on the positive side, for any continuous activation functions, the loss surface of a class of wide networks has no sub-optimal basins, where "basin" is defined as the set-wise strict local minimum; on the negative side, for a large class of networks with width below a threshold, we construct strict local minima that are not global. These two results together show the phase transition from narrow to wide networks.

📄 PDF Abstract BibTeX arXiv:1812.11039

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Affine Coupling 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Topological properties of basins of attraction and expressiveness of width bounded neural networks

2020-11-10 · Hans-Peter Beise, Steve Dias Da Cruz

In Radhakrishnan et al. [2020], the authors empirically show that autoencoders trained with usual SGD methods shape out basins of attraction around their training data. We consider network functions of width not exceedin…

Memorisation and forgetting in a learning Hopfield neural network: bifurcation mechanisms, attractors and basins

2025-08-14 · Adam E. Essex, Natalia B. Janson, Rachel A. Norris, Alexander G. Balanov arxiv

Despite explosive expansion of artificial intelligence based on artificial neural networks (ANNs), these are employed as "black boxes'', as it is unclear how, during learning, they form memories or develop unwanted featu…

Specialized Change Detection using Segment Anything

2024-08-13 · Tahir Ahmad, Sudipan Saha

Change detection (CD) is a fundamental task in Earth observation. While most change detection methods detect all changes, there is a growing need for specialized methods targeting specific changes relevant to particular …

Change DetectionEarth Observation

A Comprehensive Approach to Mode Clustering

2014-06-06 · Yen-Chi Chen, Christopher R. Genovese, Larry Wasserman

Mode clustering is a nonparametric method for clustering that defines clusters using the basins of attraction of a density estimator's modes. We provide several enhancements to mode clustering: (i) a soft variant of clus…

ClusteringDenoising

Structural Learning Theory: A Metric-Topology Factorization Approach

2026-02-08 · Xin Li arxiv

Learning in structured, multi-context, or non-stationary environments involves two orthogonal difficulties. The first is \emph{metric}: once the correct context is known, how hard is prediction within it? This is the dom…