paper-with-me

Papers

Bias-Variance Decomposition for Boltzmann Machines

2018-01-01 · ICLR 2018 1 · Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara

We achieve bias-variance decomposition for Boltzmann machines using an information geometric formulation. Our decomposition leads to an interesting phenomenon that the variance does not necessarily increase when more parameters are included in Boltzmann machines, while the bias always decreases. Our result gives a theoretical evidence of the generalization ability of deep learning architectures because it provides the possibility of increasing the representation power with avoiding the variance inflation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Transductive Boltzmann Machines

2018-05-21 · Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara

We present transductive Boltzmann machines (TBMs), which firstly achieve transductive learning of the Gibbs distribution. While exact learning of the Gibbs distribution is impossible by the family of existing Boltzmann m…

Transductive Learning

Sample Space Truncation on Boltzmann Machines

2020-10-19 · NeurIPS Workshop DL-IG 2020 12 · Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara

We present a lightweight variant of Boltzmann machines via sample space truncation, called a truncated Boltzmann machine (TBM), which has not been investigated before while can be naturally introduced from the log-linear…

Elastic regularization in restricted Boltzmann machines: Dealing with $p\gg N$

2015-10-13 · Sai Zhang

Restricted Boltzmann machines (RBMs) are endowed with the universal power of modeling (binary) joint distributions. Meanwhile, as a result of their confining network structure, training RBMs confronts less difficulties (…

Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence

2013-12-20 · Mathias Berglund, Tapani Raiko

Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) are popular methods for training the weights of Restricted Boltzmann Machines. However, both methods use an approximate method for sampling from the…

Bias-Variance Trade-Off in Hierarchical Probabilistic Models Using Higher-Order Feature Interactions

2019-06-28 · Simon Luo, Mahito Sugiyama

Hierarchical probabilistic models are able to use a large number of parameters to create a model with a high representation power. However, it is well known that increasing the number of parameters also increases the com…