- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper proposes that grokking is a result of train-validation set misalignment between low loss regions (LLR). They further suggest that known indicators of grokking (Fourier circuits, Slingshot effects, etc.) are correlates of this more fundamental cause. Specifically, the model has to move from a train-set-only LLR to a LLR that applies to both train and validation set. Hyperparameter (e.g. weight decay or learning rate) effects are then said to affect the transition from the former to the latter. An additional implication is that if the LLRs are aligned, no grokking occurs.
To support this idea they provide the following support:
- An empirically supported conjecture that the dataset-wide LLR is a single path-connected region.
- An "anti-grokking" scenario, where they manipulate the train/valid split in the original Power et al. modular-arithmetic setting to prevent grokking while not changing indicators to an extent.
- A phase diagram analysis that shows that as the train set increases (through nested subsets of an overall dataset), memorization decreases and comprehension tends to increase across multiple hyperparameter settings.
Critical strengths
- The overall perspective on loss landscape geometry / mode connectivity is intuitive and easy to follow. Also, they reinterpret existing literature on the subject instead of discarding it.
- The "anti-grokking" experiment is a genuinely interesting modification to the existing modular-arithmetic of the original grokking paper. The implications of symmetries among splits (and effective information entropy carried by the train set partition) is worth highlighting and probing further.
I name these points to motivate my suggestion for a "weak reject" instead of a strong one. If the critique below can be addressed I can see it warranting an acceptance.
Critical weaknesses
- The description of grokking is bordering on circular
- The "analysis framework" is schematic. For example, it does not suggest why or when a model would move from LLR(D_train) to LLR(D_train + D_val). Having to move from LLR(D_train) to LLR(D_train + D_val) is part of the definition of grokking and in the absence of a misalignment it does not need to happen since most of the healthy training outcomes are in LLR(D_train + D_val). Without some description of why the transition would occur it is hard to see it as a satisfying account of the cause of grokking.
- "Alignment" is never defined precisely or measured quantitively even though it is part of the core thesis of the paper. Without defining alignment before probing it in an experiment like Fig 7 it is difficult to determine if the outcome reflects alignment or something else. In Fig 7 the aim is to suggest alignment but then a lack of alignment (through a lack of effective information carried by the train set) is invoked to justify the lack of grokking.
- Experimental support is light
- The empirical support for conjecture 1 is based on an experiment presented in the appendix and it only extends to LLR(D_train + D_val), not to LLR(D_train) which also needs to be traversed by the model. Furthermore, this result is used to justify Fig 6 (which relates to a completely different dataset).
- The dismissal of slingshot effects or fourier components as indicators of grokking is based on two single qualitative plots per setting (end-of-training Fourier spectra; short early windows of the training-loss curve).
- The main evidence for alignment (the phase diagrams) are based on rather crude classification criteria (Appendix C). Even then the results show mostly confusion and no actual grokking.
Questions for authors
Request for clarification
- Do you have a more precise definition or measure of alignment that can be used as reference from which to interpret the results in Fig 7?
- Can you account for why the model would move from LLR(D_train) to LLR(D_train + D_val), even speculation?
- Does the epoch scaling in Appendix A ("linearly scales down as the number of training samples increase") apply to the Fig 7 sweep? If so, how many optimizer steps does each n receive, and is the batch size max or min(len(D), 65536)? A much shorter budget at large n could by itself explain the shift from Memorization to Confusion and the absence of Grokking.
Additional experiments
- Do you have experiments to show that LLR(D_train) is also a single path-connected region?
- Can you provide a more quantitative account of the slingshot effect and fourier spectra in the anti-grokking scenario?
- I would expect the results in Fig 7 to show a transition from Memorization to Grokking to Comprehension if the increase in n really makes the LLR(D_train + D_val) more significant. Can you produce such an experiment? Maybe with smaller jumps in weight decay?
3 comments
Do you have a more precise definition or measure of alignment that can be used as reference from which to interpret the results in Fig 7?
We provide a quantification in Appendix K, Figure 17.
Mathematically, a natural definition of misalignment is the accuracy gap between the training and validation partitions, integrated over the volume of LLR(D_1 + !D_2). However, this region lies in , and its volume is infeasible to compute in a high-dimensional parameter space. Therefore, we use an indirect measure instead of attempting to estimate the full volume.
Specifically, we use an optimization procedure to find an accessible point in LLR(D_1 + !D_2) with low training loss and high validation loss. The size of the train–validation accuracy gap, together with how easily such a point can be found, serves as a proxy for misalignment. A larger gap and easier access indicate greater misalignment, whereas a smaller gap or failure to find such a point indicates better alignment.
Can you account for why the model would move from LLR(D_train) to LLR(D_train + D_val), even speculation?
The full answer is provided in Appendix J.
This question can be answered by plotting the grokking training-loss curve on a logarithmic scale. The plot shows that training loss continues to decrease after training accuracy reaches 100%. Because the modular dataset is noise-free, correctly classified examples can still have nonzero cross-entropy. Therefore, the training loss can continue decreasing and its gradient can remain nonzero after accuracy saturates. The eventual destination depends on the effective information carried by the training partition, as illustrated by our anti-grokking experiment.
Does the epoch scaling in Appendix A ("linearly scales down as the number of training samples increase") apply to the Fig 7 sweep? If so, how many optimizer steps does each n receive, and is the batch size max or min(len(D), 65536)? A much shorter budget at large n could by itself explain the shift from Memorization to Confusion and the absence of Grokking.
The epoch scaling also applies to the Fig 7 sweeps. The scaling ensures that the number of optimization steps is greater than the n=97 baseline as the task becomes more complicated. We add the formula to Appendix A.
The total batch size and epochs are listed in the table below.
| Batch size | Epochs | |
|---|---|---|
| 97 | 9,409 | 150,000 |
| 197 | 38,809 | 150,000 |
| 297 | 65,536 | 150,000 |
| 397 | 65,536 | 53,034 |
| 497 | 65,536 | 53,034 |
| 597 | 65,536 | 28,868 |
| 697 | 65,536 | 18,750 |
| 797 | 65,536 | 13,417 |
| 897 | 65,536 | 8,100 |
| 997 | 65,536 | 6,630 |
| 1997 | 65,536 | 2,000 |
Can you provide a more quantitative account of the slingshot effect and fourier spectra in the anti-grokking scenario?
Reviewer 1 correctly pointed out that our result does not refute the Slingshot claim: it shows that Slingshots can occur without grokking by changing dataset types, so their presence is not sufficient to guarantee grokking. We have revised the text to state this distinction precisely.
Regarding quantification, the original Slingshot paper likewise characterizes the effect using training loss and accuracy rather than a separate quantitative metric. So we do not have quantitative metric to compare to, either.
I don't believe the work can be published at this point
Hi authors!
- (Appendix J) I understand that the training loss can keep decreasing after 100% train accuracy. Appendix J explains why optimization continues, but not why it ends up in the overlap LLR(D_train + D_val) rather than staying in the train-only region LLR(D_train + !D_val). That part is deferred to "effective information", which is not defined. Without it, the account of why grokking happens remains a description of the phenomenon rather than an explanation of it.
- (Appendix K) My request for a measure of misalignment was not for its own sake. The proxy in Appendix K is only reported; it is not used to support the claims in Fig. 7, Appendix F, or the anti-grokking split. I asked for it so that misalignment could be established independently of the outcome. Currently, the explanation for the absence of grokking in Fig. 7 (the regions align before the task becomes learnable) is inferred from that absence itself, since neither threshold is measured. This is the circularity I am concerned about.
- (Appendix F) This is progress towards moving away from a schematic account of grokking, and more than "a nice after-class exercise". The ideas of effective training information entropy, task-relevant information, task complexity and model capacity are in the right direction for characterizing why grokking happens. However, as the appendix itself states, these are "qualitative bookkeeping variables rather than formal measurements", which is too imprecise for a principled characterization at this stage.
I suggest developing the ideas in Appendix F further. I feel the work cannot be published in its current form.
We thank the reviewer for the careful reading and constructive comments.
Newly added Appendix J explains why optimization continues after training accuracy reaches 100%. Training accuracy records only whether the prediction is correct; it does not imply that the training cross-entropy or its gradient is zero. Because the modular dataset is noise-free, correctly classified examples can still have nonzero cross-entropy. Therefore, the training loss can continue decreasing after training accuracy reaches 100%.
The model can consequently move through the training-only region and into the overlap when that overlap is accessible. The eventual destination depends on the effective information carried by the training partition, as illustrated by the anti-grokking example. In this sense, the LLR geometry determines which regions are available, while the optimization settings determine the trajectory through them.
The ideal measure would be the volume of LLR(train+!val), but computing this volume is infeasible in the high-dimensional parameter space.
Appendix K therefore introduces an optimization-based proxy in Figure 17. Starting from the same initialization, we combine normalized training and validation gradients to decrease training loss while increasing validation loss. The resulting train–validation accuracy gap indicates how easily an accessible train-only solution can be found. We emphasize that this is a proxy for misalignment, not a direct measurement of LLR volume. Figure 7 provides a separate indirect probe through the distribution of phase cells.
Misalignment is caused by "effective training information is insufficient for the model capacity"
The lack of grokking is caused by "effective training information is insufficient for the task".
When effective training information increases, if the alignment happens earlier than "sufficient for the task", then grokking will never occur. This is the reason grokking is absent in Fig. 7.
Please see Appendix F for details about how to reproduce grokking.
Under the constraint-based heuristic in Eq. 5, a point with low loss on the full dataset is expected to have low loss on the subset of the dataset under the same threshold.
Thus, full-dataset mode connectivity motivates mode connectivity for subset of the dataset.
We also provide empirical results for the mode connectivity on the training partition of dataset xy to address the reviewer's concern, see Figure 9.
Appendix C adapts the criteria from Appendix A of existing grokking work [1]. We replace the fixed number of training steps with an adaptive time point, defined as when training accuracy first reaches 95%, so that the criteria remain comparable across datasets.
We appreciate this question because it could be a nice after-class exercise. Newly added Appendix F explains why Grokking cells are absent and how to reproduce them.
In brief, grokking requires the task-learnability threshold (anti-grokking example) to be reached before the alignment threshold. In the D_1997 sweep, these thresholds occur in the opposite order, so the intermediate grokking cells are skipped. Sampling more weight-decay values would not change this threshold ordering.
The solution is to reduce the task complexity by changing the fixed modulus from 1997 to 997, while keeping the phase-diagram procedure fixed. Grokking cells reappear at n=197, 397, and 597.
[1] https://arxiv.org/pdf/2205.10343