paper-with-me

홈 › Papers

Towards universal neural nets: Gibbs machines and ACE

2015-08-26 · Galin Georgiev

We study from a physics viewpoint a class of generative neural nets, Gibbs machines, designed for gradual learning. While including variational auto-encoders, they offer a broader universal platform for incrementally adding newly learned features, including physical symmetries. Their direct connection to statistical physics and information geometry is established. A variational Pythagorean theorem justifies invoking the exponential/Gibbs class of probabilities for creating brand new objects. Combining these nets with classifiers, gives rise to a brand of universal generative neural nets - stochastic auto-classifier-encoders (ACE). ACE have state-of-the-art performance in their class, both for classification and density estimation for the MNIST data set.

📄 PDF Abstract BibTeX arXiv:1508.06585

Code (1)

galinngeorgiev/ACE 공식 구현

Tasks

Density EstimationGeneral Classification

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

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines

2025-01-16 · Hwijae Son

Deep Operator Networks (DeepONets) are among the most prominent frameworks for operator learning, grounded in the universal approximation theorem for operators. However, training DeepONets typically requires significant …

Operator learning

Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data

2025-03-13 · Dibyakanti Kumar, Samyak Jha, Anirbit Mukherjee

In this work, we will establish that the Langevin Monte-Carlo algorithm can learn depth-2 neural nets of any size and for any data and we give non-asymptotic convergence rates for it. We achieve this via showing that und…

Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets

2019-06-26 · Amir R. Asadi, Emmanuel Abbe

We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical co…

A phase transition in sampling from Restricted Boltzmann Machines

2024-10-10 · Youngwoo Kwon, Qian Qin, Guanyang Wang, Yuchen Wei

Restricted Boltzmann Machines are a class of undirected graphical models that play a key role in deep learning and unsupervised learning. In this study, we prove a phase transition phenomenon in the mixing time of the Gi…