Erika Varis Doggett<p>This MicroAdam paper from <a href="https://mas.to/tags/NeurIPS2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NeurIPS2024</span></a> is nicely written! The algorithm is walked through in plain language first, and all the equations and proofs placed in the appendix. Super understandable, kudos to the authors. <br><a href="https://arxiv.org/abs/2405.15593" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2405.15593</span><span class="invisible"></span></a><br><a href="https://mas.to/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mas.to/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mas.to/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> <a href="https://mas.to/tags/optimizers" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>optimizers</span></a></p>
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:
654active users
sigmoid.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.3.7
#optimizers
0 posts · 0 participants · 0 posts today
JMLR<p>'PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates', by Zachary Frangella, Pratik Rathore, Shipu Zhao, Madeleine Udell.</p><p><a href="http://jmlr.org/papers/v25/23-1187.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-1187.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/optimization" class="mention hashtag" rel="tag">#<span>optimization</span></a> <a href="https://sigmoid.social/tags/preconditioned" class="mention hashtag" rel="tag">#<span>preconditioned</span></a></p>
JMLR<p>'PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization', by Qiqi Duan et al.</p><p><a href="http://jmlr.org/papers/v25/23-0386.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0386.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/optimization" class="mention hashtag" rel="tag">#<span>optimization</span></a> <a href="https://sigmoid.social/tags/pypop7" class="mention hashtag" rel="tag">#<span>pypop7</span></a></p>
JMLR<p>'Multi-Objective Neural Architecture Search by Learning Search Space Partitions', by Yiyang Zhao, Linnan Wang, Tian Guo.</p><p><a href="http://jmlr.org/papers/v25/23-1013.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-1013.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/optimizer" class="mention hashtag" rel="tag">#<span>optimizer</span></a> <a href="https://sigmoid.social/tags/optimizations" class="mention hashtag" rel="tag">#<span>optimizations</span></a></p>
JMLR<p>'Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning', by Maximilian Hüttenrauch, Gerhard Neumann.</p><p><a href="http://jmlr.org/papers/v25/22-0564.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-0564.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/reinforcement" class="mention hashtag" rel="tag">#<span>reinforcement</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/optimizes" class="mention hashtag" rel="tag">#<span>optimizes</span></a></p>
JMLR<p>'Neural Feature Learning in Function Space', by Xiangxiang Xu, Lizhong Zheng.</p><p><a href="http://jmlr.org/papers/v25/23-1202.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-1202.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/features" class="mention hashtag" rel="tag">#<span>features</span></a> <a href="https://sigmoid.social/tags/feature" class="mention hashtag" rel="tag">#<span>feature</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a></p>
JMLR<p>'Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training', by Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan.</p><p><a href="http://jmlr.org/papers/v25/23-1073.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-1073.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/accelerated" class="mention hashtag" rel="tag">#<span>accelerated</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/adaptive" class="mention hashtag" rel="tag">#<span>adaptive</span></a></p>
JMLR<p>'Scaling the Convex Barrier with Sparse Dual Algorithms', by Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H.S. Torr, M. Pawan Kumar.</p><p><a href="http://jmlr.org/papers/v25/21-0076.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/21-0076.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/sparse" class="mention hashtag" rel="tag">#<span>sparse</span></a> <a href="https://sigmoid.social/tags/dual" class="mention hashtag" rel="tag">#<span>dual</span></a></p>
JMLR<p>'Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks', by Dong-Young Lim, Sotirios Sabanis.</p><p><a href="http://jmlr.org/papers/v25/22-0796.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/22-0796.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/langevin" class="mention hashtag" rel="tag">#<span>langevin</span></a> <a href="https://sigmoid.social/tags/adaptive" class="mention hashtag" rel="tag">#<span>adaptive</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a></p>
JMLR<p>'Improving physics-informed neural networks with meta-learned optimization', by Alex Bihlo.</p><p><a href="http://jmlr.org/papers/v25/23-0356.html" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">http://</span><span class="ellipsis">jmlr.org/papers/v25/23-0356.ht</span><span class="invisible">ml</span></a> <br /> <br /><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/learnable" class="mention hashtag" rel="tag">#<span>learnable</span></a> <a href="https://sigmoid.social/tags/learned" class="mention hashtag" rel="tag">#<span>learned</span></a></p>
Published papers at TMLR<p>A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range</p><p>Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn</p><p>Action editor: Rémi Flamary.</p><p><a href="https://openreview.net/forum?id=VI2JjIfU37" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=VI2JjI</span><span class="invisible">fU37</span></a></p><p><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/imagenet" class="mention hashtag" rel="tag">#<span>imagenet</span></a> <a href="https://sigmoid.social/tags/optimizer" class="mention hashtag" rel="tag">#<span>optimizer</span></a></p>
New Submissions to TMLR<p>Auto-configuring Exploration-Exploitation Tradeoff in Population-Based Optimization: A Deep Reinforcement Learning Approach</p><p><a href="https://openreview.net/forum?id=U2viPsXLxw" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=U2viPs</span><span class="invisible">XLxw</span></a></p><p><a href="https://sigmoid.social/tags/exploration" class="mention hashtag" rel="tag">#<span>exploration</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/reinforcement" class="mention hashtag" rel="tag">#<span>reinforcement</span></a></p>
New Submissions to TMLR<p>Learning to Optimize Quasi-Newton Methods</p><p><a href="https://openreview.net/forum?id=Ns2X7Azudy" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=Ns2X7A</span><span class="invisible">zudy</span></a></p><p><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/optimizer" class="mention hashtag" rel="tag">#<span>optimizer</span></a> <a href="https://sigmoid.social/tags/hessian" class="mention hashtag" rel="tag">#<span>hessian</span></a></p>
New Submissions to TMLR<p>The Slingshot Effect: A Late-Stage Optimization Anomaly in Adaptive Gradient Methods</p><p><a href="https://openreview.net/forum?id=OZbn8ULouY" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=OZbn8U</span><span class="invisible">LouY</span></a></p><p><a href="https://sigmoid.social/tags/adaptive" class="mention hashtag" rel="tag">#<span>adaptive</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/slingshot" class="mention hashtag" rel="tag">#<span>slingshot</span></a></p>
Published papers at TMLR<p>Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques</p><p>Filip Hanzely, Boxin Zhao, mladen kolar</p><p>Action editor: Naman Agarwal.</p><p><a href="https://openreview.net/forum?id=ilHM31lXC4" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=ilHM31</span><span class="invisible">lXC4</span></a></p><p><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/personalized" class="mention hashtag" rel="tag">#<span>personalized</span></a> <a href="https://sigmoid.social/tags/optimization" class="mention hashtag" rel="tag">#<span>optimization</span></a></p>
New Submissions to TMLR<p>A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range</p><p><a href="https://openreview.net/forum?id=VI2JjIfU37" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=VI2JjI</span><span class="invisible">fU37</span></a></p><p><a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a> <a href="https://sigmoid.social/tags/imagenet" class="mention hashtag" rel="tag">#<span>imagenet</span></a> <a href="https://sigmoid.social/tags/optimizer" class="mention hashtag" rel="tag">#<span>optimizer</span></a></p>
Published papers at TMLR<p>Constrained Parameter Inference as a Principle for Learning</p><p>Nasir Ahmad, Ellen Schrader, Marcel van Gerven</p><p><a href="https://openreview.net/forum?id=CUDdbTT1QC" target="_blank" rel="nofollow noopener noreferrer" translate="no"><span class="invisible">https://</span><span class="ellipsis">openreview.net/forum?id=CUDdbT</span><span class="invisible">T1QC</span></a></p><p><a href="https://sigmoid.social/tags/backpropagation" class="mention hashtag" rel="tag">#<span>backpropagation</span></a> <a href="https://sigmoid.social/tags/neuron" class="mention hashtag" rel="tag">#<span>neuron</span></a> <a href="https://sigmoid.social/tags/optimizers" class="mention hashtag" rel="tag">#<span>optimizers</span></a></p>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload