paper-with-me

홈 › Papers

Low-loss connection of weight vectors: distribution-based approaches

2020-08-03 · ICML 2020 1 · Ivan Anokhin, Dmitry Yarotsky

Recent research shows that sublevel sets of the loss surfaces of overparameterized networks are connected, exactly or approximately. We describe and compare experimentally a panel of methods used to connect two low-loss points by a low-loss curve on this surface. Our methods vary in accuracy and complexity. Most of our methods are based on "macroscopic" distributional assumptions, and some are insensitive to the detailed properties of the points to be connected. Some methods require a prior training of a "global connection model" which can then be applied to any pair of points. The accuracy of the method generally correlates with its complexity and sensitivity to the endpoint detail.

📄 PDF Abstract BibTeX arXiv:2008.00741

Code (1)

avecplezir/distribution-based-connectivity pytorch

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

Unsupervised Learning of Distributional Relation Vectors

2018-07-01 · ACL 2018 7 · Shoaib Jameel, Zied Bouraoui, Steven Schockaert

Word embedding models such as GloVe rely on co-occurrence statistics to learn vector representations of word meaning. While we may similarly expect that co-occurrence statistics can be used to capture rich information ab…

RelationRelation ExtractionWord Embeddings

Modeling Semantic Relatedness using Global Relation Vectors

2017-11-14 · Shoaib Jameel, Zied Bouraoui, Steven Schockaert

Word embedding models such as GloVe rely on co-occurrence statistics from a large corpus to learn vector representations of word meaning. These vectors have proven to capture surprisingly fine-grained semantic and syntac…

Relation

A Thesaurus for Biblical Hebrew

2020-05-01 · LREC 2020 5 · Miriam Azar, Aliza Pahmer, Joshua Waxman

We built a thesaurus for Biblical Hebrew, with connections between roots based on phonetic, semantic, and distributional similarity. To this end, we apply established algorithms to find connections between headwords base…

Semantic SimilaritySemantic Textual Similarity

Dropout Training for Support Vector Machines

2014-04-16 · Ning Chen, Jun Zhu, Jianfei Chen, Bo Zhang

Dropout and other feature noising schemes have shown promising results in controlling over-fitting by artificially corrupting the training data. Though extensive theoretical and empirical studies have been performed for …

Data Augmentation

On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition

2018-02-20 · Marco Mondelli, Andrea Montanari

We establish connections between the problem of learning a two-layer neural network and tensor decomposition. We consider a model with feature vectors $\boldsymbol x \in \mathbb R^d$, $r$ hidden units with weights $\{\bo…

Tensor Decomposition