Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions
CC BY
Saved in:
Main Author: | |
---|---|
Format: | Book |
Language: | English |
Published: |
Springer
2023
|
Subjects: | |
Online Access: | https://link.springer.com/article/10.1007/s11590-022-01895-5 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7448 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:localhost:PNK-7448 |
---|---|
record_format |
dspace |
spelling |
oai:localhost:PNK-74482023-04-03T08:16:22Z Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions Michael C., Burkhart log-convex functions, latent state-space model CC BY To minimize the average of a set of log-convex functions, the stochastic Newton method iteratively updates its estimate using subsampled versions of the full objective’s gradient and Hessian. We contextualize this optimization problem as sequential Bayesian inference on a latent state-space model with a discriminatively-specified observation process. Applying Bayesian filtering then yields a novel optimization algorithm that considers the entire history of gradients and Hessians when forming an update. 2023-04-03T08:16:22Z 2023-04-03T08:16:22Z 2022 Book https://link.springer.com/article/10.1007/s11590-022-01895-5 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7448 en application/pdf Springer |
institution |
Digital Phenikaa |
collection |
Digital Phenikaa |
language |
English |
topic |
log-convex functions, latent state-space model |
spellingShingle |
log-convex functions, latent state-space model Michael C., Burkhart Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
description |
CC BY |
format |
Book |
author |
Michael C., Burkhart |
author_facet |
Michael C., Burkhart |
author_sort |
Michael C., Burkhart |
title |
Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
title_short |
Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
title_full |
Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
title_fullStr |
Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
title_full_unstemmed |
Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions |
title_sort |
discriminative bayesian filtering lends momentum to the stochastic newton method for minimizing log-convex functions |
publisher |
Springer |
publishDate |
2023 |
url |
https://link.springer.com/article/10.1007/s11590-022-01895-5 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7448 |
_version_ |
1762184304749707264 |
score |
8.891145 |