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!

Server stats:

599
active users

#epochs

0 posts0 participants0 posts today
JMLR<p>&#39;Scaling Data-Constrained Language Models&#39;, by Niklas Muennighoff et al.</p><p><a href="http://jmlr.org/papers/v26/24-1000.html" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v26/24-1000.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/datablations" class="mention hashtag" rel="tag">#<span>datablations</span></a> <a href="https://sigmoid.social/tags/epochs" class="mention hashtag" rel="tag">#<span>epochs</span></a> <a href="https://sigmoid.social/tags/scaling" class="mention hashtag" rel="tag">#<span>scaling</span></a></p>
💧🌏 Greg Cocks<p>Understanding Geological Time With Associate Professor Stijn Glorie [video]<br>--<br><a href="https://youtu.be/H2M2ZuVe9pE?si=iTahPKcOe2q2Yhs5" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/H2M2ZuVe9pE?si=iTahPK</span><span class="invisible">cOe2q2Yhs5</span></a> &lt;-- shared video<br>--<br>“A/Prof Stijn Glorie is a geochronologist at University of Adelaide who uses radio-isotope decay to date rocks, revealing Earth’s evolution and aiding insights into mountains, ores, and climate-tectonics links…”<br><a href="https://techhub.social/tags/geology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geology</span></a> <a href="https://techhub.social/tags/time" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>time</span></a> <a href="https://techhub.social/tags/learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>learning</span></a> <a href="https://techhub.social/tags/education" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>education</span></a> <a href="https://techhub.social/tags/dating" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dating</span></a> <a href="https://techhub.social/tags/age" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>age</span></a> <a href="https://techhub.social/tags/epochs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>epochs</span></a> <a href="https://techhub.social/tags/understanding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>understanding</span></a> <a href="https://techhub.social/tags/rocks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rocks</span></a> <a href="https://techhub.social/tags/structuralgeology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>structuralgeology</span></a> <a href="https://techhub.social/tags/Quaternary" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Quaternary</span></a> <a href="https://techhub.social/tags/conception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>conception</span></a></p>
JMLR<p>&#39;On the Generalization of Stochastic Gradient Descent with Momentum&#39;, by Ali Ramezani-Kebrya, Kimon Antonakopoulos, Volkan Cevher, Ashish Khisti, Ben Liang.</p><p><a href="http://jmlr.org/papers/v25/22-0068.html" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-0068.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/sgd" class="mention hashtag" rel="tag">#<span>sgd</span></a> <a href="https://sigmoid.social/tags/epochs" class="mention hashtag" rel="tag">#<span>epochs</span></a> <a href="https://sigmoid.social/tags/generalization" class="mention hashtag" rel="tag">#<span>generalization</span></a></p>
Published papers at TMLR<p>Empirical Limitations of the NTK for Understanding Scaling Laws in Deep Learning</p><p>Nikhil Vyas, Yamini Bansal, Preetum Nakkiran</p><p>Action editor: Jinwoo Shin.</p><p><a href="https://openreview.net/forum?id=Y3saBb7mCE" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=Y3saBb</span><span class="invisible">7mCE</span></a></p><p><a href="https://sigmoid.social/tags/scaling" class="mention hashtag" rel="tag">#<span>scaling</span></a> <a href="https://sigmoid.social/tags/epochs" class="mention hashtag" rel="tag">#<span>epochs</span></a> <a href="https://sigmoid.social/tags/empirical" class="mention hashtag" rel="tag">#<span>empirical</span></a></p>
New Submissions to TMLR<p>Limitations of the NTK for Understanding Generalization in Deep Learning</p><p><a href="https://openreview.net/forum?id=Y3saBb7mCE" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=Y3saBb</span><span class="invisible">7mCE</span></a></p><p><a href="https://sigmoid.social/tags/generalization" class="mention hashtag" rel="tag">#<span>generalization</span></a> <a href="https://sigmoid.social/tags/epochs" class="mention hashtag" rel="tag">#<span>epochs</span></a> <a href="https://sigmoid.social/tags/scaling" class="mention hashtag" rel="tag">#<span>scaling</span></a></p>
New Submissions to TMLR<p>Deep Double Descent via Smooth Interpolation</p><p><a href="https://openreview.net/forum?id=fempQstMbV" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=fempQs</span><span class="invisible">tMbV</span></a></p><p><a href="https://sigmoid.social/tags/deep" class="mention hashtag" rel="tag">#<span>deep</span></a> <a href="https://sigmoid.social/tags/overparameterized" class="mention hashtag" rel="tag">#<span>overparameterized</span></a> <a href="https://sigmoid.social/tags/epochs" class="mention hashtag" rel="tag">#<span>epochs</span></a></p>