#optimizers — Public Fediverse posts

Efficient E-Matching for Super Optimizers

https://blog.vortan.dev/ematching/

#HackerNews #Efficient #E-Matching #Super #Optimizers #E-Matching #Technology #Optimization

Efficient E-Matching for Super Optimizers

https://blog.vortan.dev/ematching/

#HackerNews #Efficient #E-Matching #Super #Optimizers #E-Matching #Technology #Optimization

'PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates', by Zachary Frangella, Pratik Rathore, Shipu Zhao, Madeleine Udell.

http://jmlr.org/papers/v25/23-1187.html

#optimizers #optimization #preconditioned

'PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates', by Zachary Frangella, Pratik Rathore, Shipu Zhao, Madeleine Udell.

http://jmlr.org/papers/v25/23-1187.html

#optimizers #optimization #preconditioned

'PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization', by Qiqi Duan et al.

http://jmlr.org/papers/v25/23-0386.html

#optimizers #optimization #pypop7

'PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization', by Qiqi Duan et al.

http://jmlr.org/papers/v25/23-0386.html

#optimizers #optimization #pypop7

'Multi-Objective Neural Architecture Search by Learning Search Space Partitions', by Yiyang Zhao, Linnan Wang, Tian Guo.

http://jmlr.org/papers/v25/23-1013.html

#optimizers #optimizer #optimizations

'Multi-Objective Neural Architecture Search by Learning Search Space Partitions', by Yiyang Zhao, Linnan Wang, Tian Guo.

http://jmlr.org/papers/v25/23-1013.html

#optimizers #optimizer #optimizations

'Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning', by Maximilian Hüttenrauch, Gerhard Neumann.

http://jmlr.org/papers/v25/22-0564.html

#reinforcement #optimizers #optimizes

'Robust Black-Box Optimization for Stochastic Search and Episodic Reinforcement Learning', by Maximilian Hüttenrauch, Gerhard Neumann.

http://jmlr.org/papers/v25/22-0564.html

#reinforcement #optimizers #optimizes

'Neural Feature Learning in Function Space', by Xiangxiang Xu, Lizhong Zheng.

http://jmlr.org/papers/v25/23-1202.html

#features #feature #optimizers

'Neural Feature Learning in Function Space', by Xiangxiang Xu, Lizhong Zheng.

http://jmlr.org/papers/v25/23-1202.html

#features #feature #optimizers

'Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training', by Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan.

http://jmlr.org/papers/v25/23-1073.html

#accelerated #optimizers #adaptive

'Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training', by Pan Zhou, Xingyu Xie, Zhouchen Lin, Kim-Chuan Toh, Shuicheng Yan.

http://jmlr.org/papers/v25/23-1073.html

#accelerated #optimizers #adaptive

'Scaling the Convex Barrier with Sparse Dual Algorithms', by Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H.S. Torr, M. Pawan Kumar.

http://jmlr.org/papers/v25/21-0076.html

#optimizers #sparse #dual

'Scaling the Convex Barrier with Sparse Dual Algorithms', by Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel, Philip H.S. Torr, M. Pawan Kumar.

http://jmlr.org/papers/v25/21-0076.html

#optimizers #sparse #dual

'Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks', by Dong-Young Lim, Sotirios Sabanis.

http://jmlr.org/papers/v25/22-0796.html

#langevin #adaptive #optimizers

'Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks', by Dong-Young Lim, Sotirios Sabanis.

http://jmlr.org/papers/v25/22-0796.html

#langevin #adaptive #optimizers

'Improving physics-informed neural networks with meta-learned optimization', by Alex Bihlo.

http://jmlr.org/papers/v25/23-0356.html

#optimizers #learnable #learned

'Improving physics-informed neural networks with meta-learned optimization', by Alex Bihlo.

http://jmlr.org/papers/v25/23-0356.html

#optimizers #learnable #learned

A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range

Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

Action editor: Rémi Flamary.

https://openreview.net/forum?id=VI2JjIfU37

#optimizers #imagenet #optimizer

A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range

Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

Action editor: Rémi Flamary.

https://openreview.net/forum?id=VI2JjIfU37

#optimizers #imagenet #optimizer

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

Filip Hanzely, Boxin Zhao, mladen kolar

Action editor: Naman Agarwal.

https://openreview.net/forum?id=ilHM31lXC4

#optimizers #personalized #optimization

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

Filip Hanzely, Boxin Zhao, mladen kolar

Action editor: Naman Agarwal.

https://openreview.net/forum?id=ilHM31lXC4

#optimizers #personalized #optimization

Constrained Parameter Inference as a Principle for Learning

Nasir Ahmad, Ellen Schrader, Marcel van Gerven

https://openreview.net/forum?id=CUDdbTT1QC

#backpropagation #neuron #optimizers

Constrained Parameter Inference as a Principle for Learning

Nasir Ahmad, Ellen Schrader, Marcel van Gerven

https://openreview.net/forum?id=CUDdbTT1QC

#backpropagation #neuron #optimizers

#update

it is now evolving into a #meta #physics #engine #MetaPhysics #PhysicsEngine

a #protocol #dedicating #its #self to the #optimization of #optimizers

#update

it is now evolving into a #meta #physics #engine #MetaPhysics #PhysicsEngine

a #protocol #dedicating #its #self to the #optimization of #optimizers

A wild #blog post appears!

Let's study the #LLVM and #GCC optimizers around the question of increments and decrements and see how they differ. Then we can make a decision as to whether or not we want to teach those optimizations to our #QBE optimizer we've been working on.

https://briancallahan.net/blog/20220417.html

#compile #compilers #optimizer #optimizers #compile #optimize #unix #c #programming #program #bsd #openbsd #freebsd #netbsd #dragonflybsd #linux #cproc

A new #blog post appears!

Let's hand-optimize the TCC code generator.

https://briancallahan.net/blog/20220406.html

#compiler #compilers #compile #compilation #optimize #optimizer #optimizers #C #unix #tcc #openbsd #freebsd #netbsd #dragonflybsd #bsd #linux

Time for a new #blog post!

We finish up our peephole optimizer, O, from the previous post. Now it's a completed framework that plugs into the cproc C compiler. So if we find that QBE is missing any more obvious optimizations, we can teach those optimizations to our peephole optimizer so we can benefit until QBE catches up.

https://briancallahan.net/blog/20220402.html

#compiler #optimizer #compile #compilers #compilation #optimizers #optimization #c #unix #bsd #openbsd #freebsd #netbsd #dragonflybsd #linux

A wild #blog post appears!

I wrote a peephole optimizer for QBE. QBE missed a couple of easy optimization wins, so let's use it as an opportunity to learn how peephole optimizers work and write one of our own.

https://briancallahan.net/blog/20220330.html

#compiler #compilers #compilation #compile #optimize #optimizer #optimizers #unix #openbsd #netbsd #freebsd #dragonflybsd #linux #c #cproc #qbe