How to Train Your Wide Neural Network Without Backprop: An Input-Weight
Alignment Perspective

How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective

15 June 2021

Akhilan Boopathy

Ila Fiete

Papers citing "How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective"

7 / 7 papers shown

Title
Training neural networks without backpropagation using particles Deepak Kumar 78 0 0 07 Dec 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark Yihua Zhang Pingzhi Li Junyuan Hong Jiaxiang Li Yimeng Zhang ... Wotao Yin Mingyi Hong Zhangyang Wang Sijia Liu Tianlong Chen 25 45 0 18 Feb 2024
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training Aochuan Chen Yimeng Zhang Jinghan Jia James Diffenderfer Jiancheng Liu Konstantinos Parasyris Yihua Zhang Zheng-Wei Zhang B. Kailkhura Sijia Liu 30 43 0 03 Oct 2023
Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis Mitchell Ostrow Adam J. Eisen L. Kozachkov Ila Fiete 38 24 0 16 Jun 2023
Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural Networks Zachary Robertson Oluwasanmi Koyejo 23 0 0 02 Jun 2023
Polarity is all you need to learn and transfer faster Qingyang Wang Michael A. Powell Ali Geisa Eric W. Bridgeford Joshua T. Vogelstein 31 3 0 29 Mar 2023
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks Blake Bordelon C. Pehlevan 41 22 0 05 Oct 2022