https://marovi.ai/index.php?action=history&feed=atom&title=Translations%3AStochastic_Gradient_Descent%2F25%2Fen 2026-04-27T22:02:27Z Revision history for this page on the wiki MediaWiki 1.39.1 https://marovi.ai/index.php?title=Translations:Stochastic_Gradient_Descent/25/en&diff=13061&oldid=prev 2026-04-27T19:42:03Z

<p>Importing a new version from external source</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 19:42, 27 April 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l7">Line 7:</td> <td colspan="2" class="diff-lineno">Line 7:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;Nesterov accelerated gradient&#039;&#039;&#039; || Evaluates the gradient at a &quot;look-ahead&quot; position || Nesterov, 1983</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;Nesterov accelerated gradient&#039;&#039;&#039; || Evaluates the gradient at a &quot;look-ahead&quot; position || Nesterov, 1983</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;<del style="font-weight: bold; text-decoration: none;">Adagrad</del>&#039;&#039;&#039; || Per-parameter rates that shrink for frequently updated features || Duchi et al., 2011</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;<ins style="font-weight: bold; text-decoration: none;">{{Term|adagrad}}</ins>&#039;&#039;&#039; || Per-parameter rates that shrink for frequently updated features || Duchi et al., 2011</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;RMSProp&#039;&#039;&#039; || Fixes <del style="font-weight: bold; text-decoration: none;">Adagrad</del>&#039;s diminishing rates using a moving average of squared gradients || Hinton (lecture notes), 2012</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;RMSProp&#039;&#039;&#039; || Fixes <ins style="font-weight: bold; text-decoration: none;">{{Term|adagrad}}</ins>&#039;s diminishing rates using a moving average of squared gradients || Hinton (lecture notes), 2012</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;{{Term|Adam}}&#039;&#039;&#039; || Combines {{Term|momentum}} with RMSProp-style adaptive rates || Kingma &amp; Ba, 2015</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;{{Term|Adam}}&#039;&#039;&#039; || Combines {{Term|momentum}} with RMSProp-style adaptive rates || Kingma &amp; Ba, 2015</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|-</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;AdamW&#039;&#039;&#039; || Decouples weight decay from the adaptive gradient step || Loshchilov &amp; Hutter, 2019</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>| &#039;&#039;&#039;AdamW&#039;&#039;&#039; || Decouples <ins style="font-weight: bold; text-decoration: none;">{{Term|</ins>weight decay<ins style="font-weight: bold; text-decoration: none;">}} </ins>from the adaptive gradient step || Loshchilov &amp; Hutter, 2019</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>|}</div></td></tr> <!-- diff cache key mediawiki:diff::1.12:old-3329:rev-13061 --> </table>

FuzzyBot https://marovi.ai/index.php?title=Translations:Stochastic_Gradient_Descent/25/en&diff=3329&oldid=prev 2026-04-27T00:35:51Z

<p>Importing a new version from external source</p> <p><b>New page</b></p><div>{| class=&quot;wikitable&quot;<br /> |-<br /> ! Method !! Key idea !! Reference<br /> |-<br /> | &#039;&#039;&#039;{{Term|momentum|Momentum}}&#039;&#039;&#039; || Accumulates an exponentially decaying moving average of past gradients || Polyak, 1964<br /> |-<br /> | &#039;&#039;&#039;Nesterov accelerated gradient&#039;&#039;&#039; || Evaluates the gradient at a &quot;look-ahead&quot; position || Nesterov, 1983<br /> |-<br /> | &#039;&#039;&#039;Adagrad&#039;&#039;&#039; || Per-parameter rates that shrink for frequently updated features || Duchi et al., 2011<br /> |-<br /> | &#039;&#039;&#039;RMSProp&#039;&#039;&#039; || Fixes Adagrad&#039;s diminishing rates using a moving average of squared gradients || Hinton (lecture notes), 2012<br /> |-<br /> | &#039;&#039;&#039;{{Term|Adam}}&#039;&#039;&#039; || Combines {{Term|momentum}} with RMSProp-style adaptive rates || Kingma &amp; Ba, 2015<br /> |-<br /> | &#039;&#039;&#039;AdamW&#039;&#039;&#039; || Decouples weight decay from the adaptive gradient step || Loshchilov &amp; Hutter, 2019<br /> |}</div>

FuzzyBot