- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
The paper proposes a new phenomenon called accuracy well. In this phenomenon, prediction accuracy rises quickly under small initialization, only to drop later on together with training loss, followed by a final increasing in accuracy with consistently low loss. The paper shows this pattern on a set of small model experiments and aims at providing the underlying theory to explain it as well.
Critical strengths
- The accuracy well phenomenon is shown across different empirical setups and with a clear causal reason.
Critical weaknesses
- The motivation on why investigating the proposed phenomenon is valuable to the broader research community is unclear. The obvious relevant related work is grokking and double descent. Both show similar patterns in different ways but the paper only briefly mentions their connection without further comparisons to relevant work such as [1, 2].
- Generally, it is not favorable that related work is moved to the appendix. The corresponding pages are lengthy and only provide limited aid for positioning the proposed work.
- The difference between when early memorization (grokking) vs. early generalization happens would be insightful but is not fully clear. This is made more challenging as it is not consistently clear which accuracy, train or validation, is shown and discussed in the paper (e.g. Figure 2 center, Figure 3).
- The theory in the main paper does not aid in understanding the accuracy well phenomenon itself. It is hard to follow and lacks the structure necessary to communicate the underlying ideas. The extensive proofs in the appendix complicate this further.
- Liu et al. "Omnigrok: Grokking Beyond Algorithmic Data". ICLR 2023.
- Kumar et al. "Grokking as the Transition from Lazy to Rich Training Dynamics". ICLR 2024.
Questions for authors
- What is the connection to grokking with L2 norm phase transition? In which sense are both effects the same?
- What key message are you trying to communicate with each of the theorems? E.g., for Theorem 4.1, what is the connection between the bound for L=1 and the accuracy well effect?
6 comments
We thank the reviewer again for their constructive feedback. We have revised the manuscript to clarify two points:
-
Relation to grokking. We expanded the discussion of related phenomena in the Introduction, explicitly distinguishing the accuracy well from grokking, which concerns delayed generalization rather than nonmonotone classification accuracy itself.
-
Interpretation of the theoretical results. We improved the exposition in Section 4 and added a new Summary paragraph that explicitly connects our main theorems to their scientific implications and experimental observations. In particular, it clarifies the mechanism behind accuracy wells, the separation between accuracy and loss dynamics, and the roles of network depth and the learning target.
We hope these revisions address the reviewer's concerns and would be happy to clarify any remaining questions.
I do not see any revisions and thus no revised manuscript.
My main concern about the broader applicability to the research community remains unanswered. What does the accuracy well let anyone predict or do? And while I agree that the presented accuracy well is different from grokking, it would still be helpful to elaborate on their connection, especially as both have a different yet distinct loss-accuracy mismatch during the initial training phases.
We thank the reviewer for the careful reading of our manuscript and for the constructive comments and questions.
We believe that grokking and the accuracy well are distinct phenomena. Grokking concerns delayed generalization: training accuracy improves much earlier than test accuracy. In contrast, the accuracy well concerns nonmonotone accuracy during training and can occur on both the training and test datasets, without requiring any delay between them.
For example, Fig. 2 (left) of our paper shows similar accuracy wells on both training and test data, without grokking. Conversely, for example, Fig. 2(a) of Kumar et al. (2024) and Fig. 2(b) of Liu et al. (2023) illustrate grokking without a pronounced accuracy well: training and test accuracies are monotonically non-decreasing over time (up to minor fluctuations), but test accuracy improves substantially later. Thus, an accuracy well can occur without grokking, and grokking can occur without an accuracy well.
The two phenomena are not mutually exclusive. In our exploratory experiments on modular addition, we have observed both effects in the same training trajectory. Whether their underlying mechanisms are related remains an open question.
We thank the reviewer for pointing out the ambiguity regarding training versus test accuracy. We have revised the captions of Figures 2 and 3 to explicitly specify which accuracy is displayed in each panel.
Our theorems aim to explain the main experimental observations and establish when an accuracy well can, or cannot, occur.
Why an accuracy well can occur. Consistent with the heuristic picture developed in Section 3, Theorems 4.2 and 4.5 rigorously establish the first two stages: an accurate classifier forms early, but subsequent concentration onto dominant singular modes can destroy its accuracy. For L=2, we also establish eventual recovery, yielding a complete accuracy well when AT>Ak⋆.
Why accuracy can change dramatically while loss barely changes. Theorems 4.2, 4.3, and 4.5 establish that both the initial accuracy rise and subsequent collapse can occur while the predictor remains microscopic and the loss change is asymptotically vanishing, matching our experimental observations.
Why network depth matters. Theorem 4.1 shows that for L=1, any accuracy drop is bounded by ε=1−AT, while Theorem B.5 shows that the duration of nontrivial accuracy dynamics vanishes with initialization. This explains why pronounced wells are strongly restricted for L=1, consistent with Fig. 2 (bottom right), unlike factorized networks with L≥2.
Why the dataset matters. Theorem 4.3 establishes an extreme accuracy well for random unary operations, where the accuracy trajectory asymptotically follows 0→1→0→1. Finite-width fluctuations cause the collapse even though the mean predictor remains perfectly accurate. In contrast, Theorem 4.4 proves monotone accuracy for permutation targets, where the flat singular-value spectrum eliminates the bottleneck, consistent with Fig. 5 (left column).
Why initialization scale and width matter. Theorem B.7 establishes that sufficiently large width suppresses fluctuations and allows the initial classifier to reach the target accuracy, supporting the stronger early accuracy hills observed at larger H. Theorem B.15 describes progressively deeper accuracy deterioration at later microscopic times. Combined with our timescale estimates (see our response to WhDc), this explains why smaller initialization can produce deeper accuracy wells by allowing more deterioration before nonlinear recovery begins.
We are currently revising the manuscript to address these comments. In particular, we plan to add a discussion distinguishing the accuracy well from grokking in the Introduction and further clarify the connection between our theoretical results, their underlying mechanisms, and the experimental observations.