On Tracking The Partition Function

By Guillaume Desjardins, Aaron C. Courville, Yoshua Bengio. 2011

28 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Flow Contrastive Estimation of Energy-Based Models (2019, background): “On the other end of the spectrum of deep generative models lies the family of energy-based models (EBMs) [42, 54, 29, 77, 73, 13, 38, 55, 9, 11, 16, 18, 6].”
Representation Learning: A Review and New Perspectives (2012, background): “during training [59], which could be useful for early”
Learning Energy-Based Models by Diffusion Recovery Likelihood (2020, background): “EBMs [27, 33, 21, 47, 10, 43, 6, 7, 25, 35, 5, 11, 4, 8, 2, 12] are an appealing class of probabilistic models, which can be viewed as generative versions of discriminators [18, 26, 28, 12], yet can be learned from unlabeled data.”
Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “Energy-based Models (EBMs) [26, 48, 58, 64, 67, 68, 75, 78, 79, 120, 129, 132, 165, 170, 182, 196, 254, 281] can be viewed as one generative version of discriminators [79, 104, 131, 134], while can be learned from unlabeled input data.”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, background): “Another interesting and recently proposed option for RBMs is to track the partition function during training (Desjardins et al. , 2011), which could be useful for early stopping and reducing the cost of ordinary AIS.”
Annealing between distributions by averaging moments (2013, background): “AIS has enabled precise quantitative comparisons of powerful generative models in image statistics [7, 8] and deep learning [9, 10, 11].”
Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization (2013, background): “, to rank candidate models, or to trigger early stopping during training when the likelihood of a validation set starts to decrease, in order to avoid overfitting (Desjardins et al., 2011).”