Learning Graphical Models
On the Stochastic Stability of Deep Markov Models
In this paper, we provide sufficient conditions of DMM's stochastic stability as defined in the context of dynamical systems
Pseudo-Spherical Contrastive Divergence
However, due to the intractable partition function, they are typically trained via contrastive divergence for maximum likelihood estimation.
Tractable Function-Space Variational Inference in Bayesian Neural Networks Tim G. J. Rudner
A popular approach for estimating the predictive uncertainty of neural networks is to define a prior distribution over the network parameters, infer an approximate posterior distribution, and use it to make stochastic predictions.
Boosting with Multiple Sources
These techniques are often very effective in practice and benefit from favorable margin-based learning guarantees (Schapire et al.,
Collaborative Causal Discovery with Atomic Interventions
Structural Causal Models (SCM) framework introduced by Pearl [2009].
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect Lorenzo Noci Dept of Computer Science ETH Zürich lorenzo.noci@inf.ethz.ch Kevin Roth
The " cold posterior effect " (CPE) in Bayesian deep learning describes the uncom-forting observation that the predictive performance of Bayesian neural networks