# One-Time Soft Alignment Enables Resilient Learning without Weight Transport

arXiv: https://arxiv.org/abs/2505.20892 · HTML: https://mlsanity.com/paper/2505.20892/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 64 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [An Investigation into Neural Net Optimization via Hessian Eigenvalue Density](https://mlsanity.com/paper/1901.10159/) (2019)
- [PyHessian: Neural Networks Through the Lens of the Hessian](https://mlsanity.com/paper/1912.07145/) (2019)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation](https://mlsanity.com/paper/1602.05179/) (2016)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures](https://mlsanity.com/paper/1807.04587/) (2018)
- [Hessian-based Analysis of Large Batch Training and Robustness to Adversaries](https://mlsanity.com/paper/1802.08241/) (2018)
- [Deep Learning without Weight Transport](https://mlsanity.com/paper/1904.05391/) (2019)
- [How Important is Weight Symmetry in Backpropagation?](https://mlsanity.com/paper/1510.05067/) (2015)
- [Memory and information processing in neuromorphic systems](https://mlsanity.com/paper/1506.03264/) (2015)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Biologically-plausible learning algorithms can scale to large datasets](https://mlsanity.com/paper/1811.03567/) (2018)
- [Pretraining with Random Noise for Fast and Robust Learning without Weight Transport](https://mlsanity.com/paper/2405.16731/) (2024)
- [Pretraining with random noise for uncertainty calibration](https://mlsanity.com/paper/2412.17411/) (2024)

## Built on by (most cited first, 1 of 1)

- [Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis](https://mlsanity.com/paper/2508.01219/) (2025)

## Abstract (arXiv)

Backpropagation is the cornerstone of deep learning, but its reliance on symmetric weight transport and global synchronization makes it computationally expensive and biologically implausible. Feedback alignment offers a promising alternative by approximating error gradients through fixed random feedback, thereby avoiding symmetric weight transport. However, this approach often struggles with poor learning performance and instability, especially in deep networks. Here, we show that a one-time soft alignment between forward and feedback weights at initialization enables deep networks to achieve performance comparable to backpropagation, without requiring weight transport during learning. This simple initialization condition guides stable error minimization in the loss landscape, improving network trainability. Spectral analyses further reveal that initial alignment promotes smoother gradient flow and convergence to flatter minima, resulting in better generalization and robustness. Notably, we also find that allowing moderate deviations from exact weight symmetry can improve adversarial robustness compared to standard backpropagation. These findings demonstrate that a simple initialization strategy can enable effective learning in deep networks in a biologically plausible and resource-efficient manner.