JMLR · @jmlr
703 followers · 293 posts · Server sigmoid.social

'Posterior Consistency for Bayesian Relevance Vector Machines', by Xiao Fang, Malay Ghosh.

jmlr.org/papers/v24/20-1012.ht

#posterior #priors #relevance

Last updated 1 year ago

JMLR · @jmlr
677 followers · 279 posts · Server sigmoid.social

'Infinite-dimensional optimization and Bayesian nonparametric learning of stochastic differential equations', by Arnab Ganguly, Riten Mitra, Jinpu Zhou.

jmlr.org/papers/v24/22-0582.ht

#stochastic #sparse #priors

Last updated 1 year ago

Shih Ching Fu · @shihchingfu
94 followers · 180 posts · Server bayes.club

random walk, n., the route through an open plan office taken by a whilst waiting for their chains to converge (hopefully). Expected length of route may depend on factors such as hardware specifications, informativeness of , and whether there's a good coffee machine nearby. @pymc

#statistician #mcmc #priors #statsodon #bayesian #iamworking

Last updated 2 years ago

JMLR · @jmlr
656 followers · 186 posts · Server sigmoid.social

'Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching', by Eliezer de Souza da Silva, Tomasz Kuśmierczyk, Marcelo Hartmann, Arto Klami.

jmlr.org/papers/v24/21-0623.ht

#factorization #hyperparameters #priors

Last updated 2 years ago

JMLR · @jmlr
656 followers · 185 posts · Server sigmoid.social

'Posterior Contraction for Deep Gaussian Process Priors', by Gianluca Finocchio, Johannes Schmidt-Hieber.

jmlr.org/papers/v24/21-0556.ht

#priors #posterior #gaussian

Last updated 2 years ago

New Submissions to TMLR · @tmlrsub
163 followers · 434 posts · Server sigmoid.social

Chasing Better Deep Image Priors between Over- and Under-parameterization

openreview.net/forum?id=EwJJks

#priors #prior #deep

Last updated 2 years ago

Published papers at TMLR · @tmlrpub
498 followers · 241 posts · Server sigmoid.social

SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning

Marco Bagatella, Sammy Joe Christen, Otmar Hilliges

openreview.net/forum?id=qYNfwF

#reinforcement #exploration #priors

Last updated 2 years ago

JMLR · @jmlr
627 followers · 131 posts · Server sigmoid.social

'Learning-augmented count-min sketches via Bayesian nonparametrics', by Emanuele Dolera, Stefano Favaro, Stefano Peluchetti.

jmlr.org/papers/v24/21-0096.ht

#priors #nonparametrics #nonparametric

Last updated 2 years ago

JMLR · @jmlr
626 followers · 119 posts · Server sigmoid.social

'An Optimization-centric View on Bayes' Rule: Reviewing and Generalizing Variational Inference', by Jeremias Knoblauch, Jack Jewson, Theodoros Damoulas.

jmlr.org/papers/v23/19-1047.ht

#posteriors #priors #generalization

Last updated 2 years ago

Peter Moleman · @MolemanPeter
263 followers · 19 posts · Server neuromatch.social

@heleenslagter Menno Oosterhof has OCD and used psilicybine. It freed him in certain ways from his OCD preoccupations. I think this can be explained largely with what you and Ruben Laukkonen explained in Laukkonen RE, Slagter HA (2021): From many to (n)one: Meditation and the plasticity of the predictive mindNeuroscience & Biobehavioral Reviews 128:199–217.
So I think meditation and psilocybine might do the same. OCD must be related to rigid priors. Do you have any ideas about that. Or has anybody else for that matter?

#neuroscience #ocd #psilocybine #self #priors

Last updated 2 years ago

Peter Moleman · @MolemanPeter
263 followers · 19 posts · Server neuromatch.social

@heleenslagter Menno Oosterhof has OCD and used psilicybine. It freed him in certain ways from his OCD preocculations. I think this can be explained largely with what you and Ruben Laukkonen explained in Laukkonen RE, Slagter HA (2021): From many to (n)one: Meditation and the plasticity of the predictive mindNeuroscience & Biobehavioral Reviews 128:199–217.
So I think meditation and psilocybine might do the same. OCD must be related to rigid priors. Do you have any ideas about that. Or has anybody else for that matter?

#neuroscience #ocd #psilocybine #self #priors

Last updated 2 years ago

Aki Vehtari · @avehtari
1519 followers · 153 posts · Server bayes.club

Topic: Workflows for better priors

Bayesian models rely on prior distributions that encode knowledge about the problem, but specifying good priors is often difficult in practice. We are working on multiple fronts on making it easier, with contributions to e.g. prior elicitation, prior diagnostics, prior checking, and specification of priors in predictive spaces.

#priors #bayes

Last updated 2 years ago