fosstodon.org is one of the many independent Mastodon servers you can use to participate in the fediverse.
Fosstodon is an invite only Mastodon instance that is open to those who are interested in technology; particularly free & open source software. If you wish to join, contact us for an invite.

Administered by:

Server stats:

8.8K
active users

#invariance

0 posts0 participants0 posts today
KEXP 🎶 #NowPlaying Bot<p>🇺🇦 <a href="https://mastodonapp.uk/tags/NowPlaying" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NowPlaying</span></a> on <a href="https://mastodonapp.uk/tags/KEXP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KEXP</span></a>'s <a href="https://mastodonapp.uk/tags/VarietyMix" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VarietyMix</span></a></p><p>Invariance:<br> 🎵 Soft As The Day</p><p><a href="https://mastodonapp.uk/tags/Invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Invariance</span></a> </p><p><a href="https://invce.bandcamp.com/track/soft-as-the-day" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">invce.bandcamp.com/track/soft-</span><span class="invisible">as-the-day</span></a></p><p><a href="https://open.spotify.com/track/6jiMKyoLf0pScyot4BLAeb" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">open.spotify.com/track/6jiMKyo</span><span class="invisible">Lf0pScyot4BLAeb</span></a></p>
Dr Mircea Zloteanu ☀️ 🌊🌴<p><a href="https://mastodon.social/tags/statstab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>statstab</span></a> #239 Why Full, Partial, or Approximate Measurement Invariance Are Not a Prerequisite for Meaningful and Valid Group Comparisons</p><p>Thoughts: Item loadings should be the same across groups. This is v important &amp; also ok if not 🤷🏼‍♂️</p><p><a href="https://mastodon.social/tags/psychometrics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>psychometrics</span></a> <a href="https://mastodon.social/tags/variance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>variance</span></a> <a href="https://mastodon.social/tags/itemloading" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>itemloading</span></a> <a href="https://mastodon.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a> </p><p><a href="https://www.tandfonline.com/doi/full/10.1080/10705511.2023.2191292" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">tandfonline.com/doi/full/10.10</span><span class="invisible">80/10705511.2023.2191292</span></a></p>
JMLR<p>'Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces', by Iskander Azangulov, Andrei Smolensky, Alexander Terenin, Viacheslav Borovitskiy.</p><p><a href="http://jmlr.org/papers/v25/23-0115.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0115.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/gaussian" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gaussian</span></a> <a href="https://sigmoid.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a> <a href="https://sigmoid.social/tags/cov" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cov</span></a></p>
JMLR<p>'Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case', by Iskander Azangulov, Andrei Smolensky, Alexander Terenin, Viacheslav Borovitskiy.</p><p><a href="http://jmlr.org/papers/v25/22-1434.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-1434.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/gaussian" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gaussian</span></a> <a href="https://sigmoid.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a> <a href="https://sigmoid.social/tags/spatiotemporal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatiotemporal</span></a></p>
Pustam | पुस्तम | পুস্তম🇳🇵<p>via MathMatize@X</p><p><a href="https://mathstodon.xyz/tags/GaussianCurvature" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GaussianCurvature</span></a> <a href="https://mathstodon.xyz/tags/EigenValue" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EigenValue</span></a> <a href="https://mathstodon.xyz/tags/Isometry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Isometry</span></a> <a href="https://mathstodon.xyz/tags/Invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Invariance</span></a> <a href="https://mathstodon.xyz/tags/IsometryInvariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IsometryInvariance</span></a> <a href="https://mathstodon.xyz/tags/Pizza" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Pizza</span></a> <a href="https://mathstodon.xyz/tags/PizzaMath" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PizzaMath</span></a> <a href="https://mathstodon.xyz/tags/Maths" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Maths</span></a> <a href="https://mathstodon.xyz/tags/Math" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Math</span></a> <a href="https://mathstodon.xyz/tags/MathMeme" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MathMeme</span></a> <a href="https://mathstodon.xyz/tags/MathsMeme" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MathsMeme</span></a> <a href="https://mathstodon.xyz/tags/MathMemes" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MathMemes</span></a> <a href="https://mathstodon.xyz/tags/MathsMemes" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MathsMemes</span></a> <a href="https://mathstodon.xyz/tags/Mathematics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Mathematics</span></a> <a href="https://mathstodon.xyz/tags/Mathematicians" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Mathematicians</span></a> <a href="https://mathstodon.xyz/tags/Mathematician" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Mathematician</span></a></p>
Giulio<p><a href="https://mastodon.world/tags/Spinors" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Spinors</span></a> can be viewed as "square roots" of <a href="https://mastodon.world/tags/sections" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sections</span></a> of <a href="https://mastodon.world/tags/vector" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vector</span></a> <a href="https://mastodon.world/tags/bundles" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>bundles</span></a>.</p><p><a href="https://en.m.wikipedia.org/wiki/Spinor" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">en.m.wikipedia.org/wiki/Spinor</span><span class="invisible"></span></a></p><p><a href="https://mastodon.world/tags/Spinors" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Spinors</span></a> are mathematical entities somewhat like <a href="https://mastodon.world/tags/tensors" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tensors</span></a>, that allow a more general treatment of the notion of <a href="https://mastodon.world/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a> under <a href="https://mastodon.world/tags/rotation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rotation</span></a> and <a href="https://mastodon.world/tags/Lorentz" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lorentz</span></a> boosts.</p><p><a href="https://arxiv.org/abs/1312.3824" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/1312.3824</span><span class="invisible"></span></a></p><p><a href="https://youtu.be/b7OIbMCIfs4" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/b7OIbMCIfs4</span><span class="invisible"></span></a></p>
JMLR<p>'Effect-Invariant Mechanisms for Policy Generalization', by Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja, Susan Murphy, Jonas Peters.</p><p><a href="http://jmlr.org/papers/v25/23-0802.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0802.ht</span><span class="invisible">ml</span></a> <br> <br><a href="https://sigmoid.social/tags/causal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>causal</span></a> <a href="https://sigmoid.social/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> <a href="https://sigmoid.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a></p>
Dennis Alexis Valin Dittrich<p>Interpolation Can Provably Preclude Invariance <a href="https://arxiv.org/abs/2211.15724" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2211.15724</span><span class="invisible"></span></a><br><a href="https://fediscience.org/tags/Overfitting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Overfitting</span></a> to the point of <a href="https://fediscience.org/tags/interpolation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>interpolation</span></a> can hinder invariance-inducing objectives: One cannot assume a <a href="https://fediscience.org/tags/DeepLearninig" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearninig</span></a> model with an invariance penalty will indeed achieve any form of <a href="https://fediscience.org/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a>… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which <a href="https://fediscience.org/tags/robustness" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>robustness</span></a> or <a href="https://fediscience.org/tags/fairness" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fairness</span></a> are desirable.</p>
Yohan John 🤖🧠<p>"By definition, only amodal properties (information not specific to a particular sensory system; e.g., tempo, rhythm, duration, intensity) can be redundantly specified across the senses."</p><p>In other words, cross-modal redundancy is a type of invariance or symmetry with respect to transformation of sensory modality.</p><p><a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4316375/" rel="nofollow noopener" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">ncbi.nlm.nih.gov/pmc/articles/</span><span class="invisible">PMC4316375/</span></a></p><p>🧵 More excerpts below 👇 </p><p><a href="https://fediscience.org/tags/Neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuroscience</span></a> <a href="https://fediscience.org/tags/Psychology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Psychology</span></a> <a href="https://fediscience.org/tags/Attention" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Attention</span></a> <a href="https://fediscience.org/tags/Invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Invariance</span></a> <a href="https://fediscience.org/tags/Symmetry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Symmetry</span></a></p>
Yohan John 🤖🧠<p><span class="h-card"><a href="https://mastodon.social/@teixi" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>teixi</span></a></span> </p><p>All linguistic communication requires symbols, no?</p><p>I like to think of metaphors as latent analogies. More on this here: </p><p><a href="https://yohanjohn.com/axispraxis/metaphor-the-alchemy-of-thought/" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">yohanjohn.com/axispraxis/metap</span><span class="invisible">hor-the-alchemy-of-thought/</span></a></p><p>Both metaphor and analogy are in turn types of <a href="https://fediscience.org/tags/symmetry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>symmetry</span></a> or <a href="https://fediscience.org/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a>.</p><p><a href="https://3quarksdaily.com/3quarksdaily/2014/07/science-is-symmetry.html" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">3quarksdaily.com/3quarksdaily/</span><span class="invisible">2014/07/science-is-symmetry.html</span></a></p>
Maximilian Ilse<p><a href="https://sigmoid.social/tags/Introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Introduction</span></a> </p><p>I'm a senior researcher at Microsoft Research Health futures in Amsterdam/Cambridge.</p><p>My research interests include invariance/equivariance, causality and representation learning, especially the interplay of these 3 things. All applied to medical imaging.</p><p><a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deeplearning</span></a> <a href="https://sigmoid.social/tags/causality" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>causality</span></a> <a href="https://sigmoid.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a></p>
Esteban :linux: :rstats:<p><a href="https://fosstodon.org/tags/stats" class="mention hashtag" rel="tag">#<span>stats</span></a> <a href="https://fosstodon.org/tags/sem" class="mention hashtag" rel="tag">#<span>sem</span></a> <a href="https://fosstodon.org/tags/review" class="mention hashtag" rel="tag">#<span>review</span></a> <a href="https://fosstodon.org/tags/invariance" class="mention hashtag" rel="tag">#<span>invariance</span></a> </p><p>Interesting review by a solid and robust team on invariance testing in Sturctural Equation Modeling.<br /> <a href="https://www.sciencedirect.com/science/article/pii/S0049089X22001168?dgcid=coauthor" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://www.</span><span class="ellipsis">sciencedirect.com/science/arti</span><span class="invisible">cle/pii/S0049089X22001168?dgcid=coauthor</span></a></p>
Klaus Pforr<p>Very interesting <a href="https://mastodon.social/tags/review" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>review</span></a> paper on <a href="https://mastodon.social/tags/measurement" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>measurement</span></a> <a href="https://mastodon.social/tags/invariance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>invariance</span></a><br><a href="https://www.sciencedirect.com/science/article/abs/pii/S0049089X22001168" rel="nofollow noopener" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">sciencedirect.com/science/arti</span><span class="invisible">cle/abs/pii/S0049089X22001168</span></a></p>