- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper looks into layer-wise per-sample gradients during image classification. It finds that the cosine alignment between these per-sample gradients cluster around class labels, with intra-clusters variance correlating with generalization performance.
Critical strengths
- The key insight, that gradient directions initially cluster within class labels while becoming more dispersed during training in accordance with better generalization is interesting.
- This is also the case for the finding that alignment between clusters is not relevant for generalization. It is perhaps even possible to say that between-label clusters should not be aligned.
Critical weaknesses
- Per-sample gradient analysis itself is not "recent" (line 034) but has been analyzed in fields such as differential privacy for quite some time [1, 2].
- There is also a range of relevant related work missing, such as [3, 4, 5, 6].
- It is unclear what the compute overhead of the method is and if it would scale to larger more modern encoders and architectures. This would be particularly interesting as the motivation for some choices, such as using PCA and layer-wise per-sample gradients, is not fully clear and not properly ablated.
- It seems like PCA will only have a moderate performance gain while introducing unnecessary abstraction and potential noise.
- On the other hand, the layer-wise approach is a main differentiator to [3, 4, 5] and has only been done (in some sense) on the last layer in [6]. Focusing on the differences and insights here compared to full model or classifier head per-sample gradients would strengthen the work.
- Generally, connecting the paper's insights to approaches outside of image classification would be desirable to better fit into the current state of research.
- Martín Abadi et al. "Deep Learning with Differential Privacy". ACM SIGSAC 2016.
- Hanshen Xiao et al. "Geometry of Sensitivity: Twice Sampling and Hybrid Clipping in Differential Privacy with Optimal Gaussian Noise and Application to Deep Learning". ACM CCS 2023.
- Stanislav Fort et al. "Stiffness: A New Perspective on Generalization in Neural Networks". 2020. arXiv: 1901.09491
- Karthik A. Sankararaman et al. “The impact of neural network overparameterization on gradient confusion and stochastic gradient descent”. ICML 2020.
- Jinlong Liu et al. “Understanding Why Neural Networks Generalize Well Through GSNR of Parameters”. ICLR 2020.
- Florian A. Hölzl et al. "Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks". NeurIPS 2025.
Questions for authors
- PCA on normalized gradients is used for efficiency (line 158). Is the PCA computed at each time step? What is the cost of this PCA?
- Does Figure 5d seems kind of odd. Is it potentially desired to not have clusters aligned, i.e. similar to what we aim for in contrastive learning?