Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models

S Bond-Taylor, A Leach, Y Long… - IEEE transactions on …, 2021‏ - ieeexplore.ieee.org
Deep generative models are a class of techniques that train deep neural networks to model
the distribution of training samples. Research has fragmented into various interconnected …

Im-loss: information maximization loss for spiking neural networks

Y Guo, Y Chen, L Zhang, X Liu… - Advances in …, 2022‏ - proceedings.neurips.cc
Abstract Spiking Neural Network (SNN), recognized as a type of biologically plausible
architecture, has recently drawn much research attention. It transmits information by $0/1 …

How to train your energy-based models

Y Song, DP Kingma - ar** density-ratio estimation
B Rhodes, K Xu, MU Gutmann - Advances in neural …, 2020‏ - proceedings.neurips.cc
Density-ratio estimation via classification is a cornerstone of unsupervised learning. It has
provided the foundation for state-of-the-art methods in representation learning and …

[PDF][PDF] Information-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities.

S Yu, LGS Giraldo, JC Príncipe - IJCAI, 2021‏ - ijcai.org
We present a review on the recent advances and emerging opportunities around the theme
of analyzing deep neural networks (DNNs) with information-theoretic methods. We first …

Energy-based models for anomaly detection: A manifold diffusion recovery approach

S Yoon, YU **, YK Noh, F Park - Advances in Neural …, 2023‏ - proceedings.neurips.cc
We present a new method of training energy-based models (EBMs) for anomaly detection
that leverages low-dimensional structures within data. The proposed algorithm, Manifold …

A general recipe for likelihood-free Bayesian optimization

J Song, L Yu, W Neiswanger… - … conference on machine …, 2022‏ - proceedings.mlr.press
The acquisition function, a critical component in Bayesian optimization (BO), can often be
written as the expectation of a utility function under a surrogate model. However, to ensure …