Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

588
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.4

#GaussianProcesses

0 posts0 participants0 posts today
Shih Ching Fu<p><span class="h-card" translate="no"><a href="https://bayes.club/@charleemos" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>charleemos</span></a></span> I have found both the <a href="https://bayes.club/tags/PyMC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PyMC</span></a> tutorials (<a href="https://www.pymc.io/projects/docs/en/latest/guides/Gaussian_Processes.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">pymc.io/projects/docs/en/lates</span><span class="invisible">t/guides/Gaussian_Processes.html</span></a>) and the <a href="https://bayes.club/tags/Stan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Stan</span></a> User's Guide (<a href="https://mc-stan.org/docs/stan-users-guide/gaussian-processes.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">mc-stan.org/docs/stan-users-gu</span><span class="invisible">ide/gaussian-processes.html</span></a>) on <a href="https://bayes.club/tags/GaussianProcesses" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GaussianProcesses</span></a> good for getting your hands dirty. Seeing GPs in action and fiddling with hyperparameters was helpful for me to understand the mathematical underpinnings.</p>
Mandar Chandorkar<p>Very interesting read about spectral approximation of kernels using gauss-legendre quadrature! <a href="https://sigmoid.social/tags/GaussianProcesses" class="mention hashtag" rel="tag">#<span>GaussianProcesses</span></a> </p><p>Building on the random fourier features by Rahimi and Recht.</p><p>Liked how the authors distinguished these approaches from methods which need the data points (Nyström approximation) but are nevertheless spectral in nature. (Well dont all kernel methods pass through the spectral plane 😉 )<br /><a href="https://sigmoid.social/@jmlr/109522531551727997" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">sigmoid.social/@jmlr/109522531</span><span class="invisible">551727997</span></a></p>
Seth Axen 🪓 :julia:<p>Check out some results from one of our current projects! <a href="https://bayes.club/tags/Spatiotemporal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Spatiotemporal</span></a> modeling of European <a href="https://bayes.club/tags/paleoclimate" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paleoclimate</span></a> using doubly sparse <a href="https://bayes.club/tags/GaussianProcesses" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GaussianProcesses</span></a></p><p><a href="https://arxiv.org/abs/2211.08160" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2211.08160</span><span class="invisible"></span></a></p>
ML ⇌ Science Colaboratory<p>Our preprint "Spatiotemporal modeling of European <a href="https://fediscience.org/tags/paleoclimate" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>paleoclimate</span></a> using doubly sparse Gaussian processes" is now on <a href="https://fediscience.org/tags/arXiv" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>arXiv</span></a>!</p><p>This is one of the outcomes of a cooperation we (<span class="h-card"><a href="https://bayes.club/@sethaxen" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>sethaxen</span></a></span>, Alex Gessner, and Álvaro Tejero-Cantero) are currently running with <span class="h-card"><a href="https://fosstodon.org/@sommer" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>sommer</span></a></span> and Nils Weitzel.</p><p>The paper, as well as a lightning talk and poster, were accepted to the <a href="https://fediscience.org/tags/NeurIPS2022" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NeurIPS2022</span></a> workshop on <a href="https://fediscience.org/tags/GaussianProcesses" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GaussianProcesses</span></a>, <a href="https://fediscience.org/tags/Spatiotemporal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Spatiotemporal</span></a> Modeling, and Decision-making Systems <a href="https://fediscience.org/tags/GPSMDMS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPSMDMS</span></a></p><p><a href="https://arxiv.org/abs/2211.08160" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2211.08160</span><span class="invisible"></span></a></p>
TrendingLive feeds
About