- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies supervised binary classification with unlabeled context using a deep residual attention-only transformer. Under an orthogonal Gaussian-noise model, zero initialization, and population gradient descent, it claims small population loss after the second update and increasing layer-wise signal-to-noise ratios. The proposed mechanism is learned within-class aggregation. A downstream maximum-margin analysis is used to derive depth-dependent classification risk bounds, and synthetic, noisy-image, and task-trained GPT-2 experiments illustrate related layer-wise trends.
The objective of connecting training dynamics, denoising, and downstream representation quality is interesting. However, the main theoretical guarantees currently depend on unresolved distributional and derivational steps under the stated data model.
Critical strengths
-
Connecting the training dynamics of deep softmax attention to layer-wise signal/noise decomposition and downstream classification is a worthwhile theoretical objective. Tracking signal and noise coefficients provides an interpretable framework for examining within-class aggregation.
-
The paper attempts to analyze a trained multilayer model rather than only exhibiting hand-constructed denoising weights. The detailed appendices and experiments across synthetic data, noisy MNIST/CIFAR, and richer task-trained architectures make the proposed phenomenon concrete, although they do not resolve the proof issues below.
Critical weaknesses
-
The core training and denoising proofs use calculations inconsistent with the stated independent-label model. On p.29, step (i) replaces the sample-dependent logistic derivative with a constant −r_1. Let q=(2^{L+1}−1)/N and a=η(1+q)/2. The paper’s first-step result and uniform attention give h_N=x_N+q∑_j x_j and v^(1)=aμ, hence the query margin is a||μ||²(1+q y_N∑_j y_j). Under independent Rademacher labels, this is random, so the derivative cannot simply be pulled out of the expectation as the stated constant. Separately, p.43 replaces both class counts with N/2 and treats exact balance as without loss of generality under token reordering. Reordering cannot change class counts. Conditioning on balance also changes the first-step expected gradient, so adding a balance assumption alone does not preserve the existing formulas. These issues affect Lemma D.1 and the subsequent analysis built on it, making the central guarantees unestablished in the current version.
-
The concentration and downstream-risk arguments require additional justification. Lemma G.4 assumes constant coefficients, whereas the coefficients used in Eq. E.27 are generated by attention and depend on the same noise vectors. A fixed-coefficient Gaussian argument does not directly apply; a uniform concentration result or another valid treatment is needed. Appendix F also needs to verify the full assumptions of the cited maximum-margin theorem for the transformed features, rather than relying only on a sub-Gaussian tail claim. Finally, decreasing risk upper bounds do not prove monotonicity of actual risks. These are substantive gaps in the paper’s main theoretical contribution, beyond the first weakness.
Questions for authors
The following questions could materially change my assessment:
-
Can you correct the second-step derivative calculation on p.29 and the exact-balance substitution on p.43, specify the label distribution for the revised guarantees, and trace the corrections through Lemma D.1 and the subsequent training/SNR analysis? Please account for the fact that conditioning on exact balance changes the first-step gradient.
-
Can you provide concentration bounds valid for noise-dependent attention coefficients and verify the full assumptions of the external maximum-margin theorem for the transformed features? Please distinguish a decreasing risk upper bound from an ordering of actual classification risks.
-
What evidence isolates the benefit of unlabeled context from depth alone? A focused no-context or context-replacement control would clarify the mechanism. Please also specify the GPT-2 attention mask and token layout so that access to context by the probed token is clear.
My recommendation is rejection in the current version because the main theoretical contribution rests on the unresolved steps above. I would reconsider substantially if the proofs are repaired under a clearly stated distribution and the conclusions are appropriately scoped.
2 comments
Response 2
Q2.Can you provide concentration bounds valid for noise-dependent attention coefficients and verify the full assumptions of the external maximum-margin theorem for the transformed features? Please distinguish a decreasing risk upper bound from an ordering of actual classification risks.
W2 Appendix F also needs to verify the full assumptions of the cited maximum-margin theorem for the transformed features, rather than relying only on a sub-Gaussian tail claim. Finally, decreasing risk upper bounds do not prove monotonicity of actual risks. These are substantive gaps in the paper’s main theoretical contribution, beyond the first weakness.
AQ2&AW2: Regarding the condition verification for applying Theorem 3.1 in Cao et al. (2021) in Appendix F, Theorem 3.1 of Cao et al. (2021) assumes the data point is from a mixture of two sub-Gaussian distributions with means and respectively and the same covariance matrix .
In Appendix F, we prove that for every layer , the last-column token used in the downstream logistic regression satisfies this data model: Specifically, our data can be decomposed as . Here the first term is the signal part, and the second and third terms together form the noise part , which has zero mean and covariance matrix . Given are all bounded and are i.i.d Gaussian random variables for all , it follows that the noise term is sub-Gaussian even if they are not independent. Hence, is also sub-Gaussian random variable. The two class means are and with the same covariance matrix . Therefore, all conditions of Thm 3.1 in Cao et al. (2021) are satisfied, and the proof in Appendix F remains valid.
Our theory provides an upper bound on the population risk, showing that the increase of SNR across layers corresponds to features with more effectively captured signals, resulting in improved performance on the downstream tasks. Our experimental results support this conclusion and can help address your concern. In particular, it is observed that hidden states from deeper transformer layers achieve higher test accuracy on the downstream task, suggesting that the bound is informative in practice.
Q3:What evidence isolates the benefit of unlabeled context from depth alone? A focused no-context or context-replacement control would clarify the mechanism. Please also specify the GPT-2 attention mask and token layout so that access to context by the probed token is clear.
AQ3: We would like to emphasize that our attention-only deep transformer in Eq. (2.1) already provides a natural context-free control for studying the denoising effect of the unlabeled context. After the first training step, the vector covers the direction of the signal , but this trained linear classifier is not involved in our denoising effect analysis or in the downstream evaluation. Without such a classifier , we use only the hidden state as features in the downstream classification task.
Moreover, in this attention-stacked transformer model (2.1), if all context tokens are masked, the output hidden state reduces to the query token itself. Therefore, the model (2.1) naturally provides a baseline without context, and the effect of the context can be assessed by comparing the hidden layer features with the original input token .
Our experiments on attention-only transformers (2.1) in Sec. 5 show that, compared with the input token, utilizing the unlabeled context enables the features to capture more signal, resulting in improved downstream prediction accuracy.
Therefore, both our theoretical framework and our experiments already include a control for the unlabeled context, and they both support the conclusion that the self-attention mechanism leverages the unlabeled context to improve feature quality.
For GPT-2 experiments, we have updated our GPT-2 experiment results in the revised paper PDF (Appendix C.5-C.7, highlighted in blue in the manuscript). All experiments now use GPT-2’s standard causal mask. We also explicitly specify the query token positions used (the last few tokens) in the downstream task in the detailed description of each experimental setting. For example, in the MNIST experiments with GPT-2, the downstream classifier uses the eighth token, from layer .
Response 1
W1:The core training and denoising proofs use calculations inconsistent with the stated independent-label model. On p.29, step (i) replaces the sample-dependent logistic derivative with a constant −r_1. Let q=(2^{L+1}−1)/N and a=η(1+q)/2. The paper’s first-step result and uniform attention give h_N=x_N+q∑_j x_j and v^(1)=aμ, hence the query margin is a||μ||²(1+q y_N∑_j y_j). Under independent Rademacher labels, this is random, so the derivative cannot simply be pulled out of the expectation as the stated constant. Separately, p.43 replaces both class counts with N/2 and treats exact balance as without loss of generality under token reordering. Reordering cannot change class counts. Conditioning on balance also changes the first-step expected gradient, so adding a balance assumption alone does not preserve the existing formulas. These issues affect Lemma D.1 and the subsequent analysis built on it, making the central guarantees unestablished in the current version.
Q1.Can you correct the second-step derivative calculation on p.29 and the exact-balance substitution on p.43, specify the label distribution for the revised guarantees, and trace the corrections through Lemma D.1 and the subsequent training/SNR analysis? Please account for the fact that conditioning on exact balance changes the first-step gradient.
AW1&AQ1: For step (i) on p.29, the calculation of the second-step logistic derivative is based on the balanced population assumption. At the second iteration, the logistic derivative is ℓ′(yNf(X)eN) and we have that $y_Nf(X) e_N= y_N {v^{(1)}}^{\top}(x_N+\frac{2^{L}-1}{N}\sum_{j=1}^{N} x_j) = {v^{(1)}}^{\top}\mu+ {v^{(1)}}^{\top}\mu y_N\sum_{j=1}^{N} y_j= {v^{(1)}}^{\top}\mu $ where the first equality is by the first step training results that Wl(1)=0d×d,l=0,…,L and the last equality is by the balanced population assumption gives that ∑j=1Nyj=0. Therefore, we have ℓ′(yNf(X)eN)=ℓ′(v(1)⊤μ), thus this term is a constant that can be pulled out of the expectation.
For the joint sampling scheme, the balanced population assumption will be applied to the N context tokens. The query token will be re-indexed as xN+1, with an independent Rademacher label yN+1. The query token is masked from the intermediate context-processing layers and enters only through the final query readout. Thus, the balance assumption applies only to the context tokens and does not constrain the query label.
Regarding the reordering of the token in Appendix E.2 (p.43), we agree that reordering alone cannot give equal class counts. The equation yi=1,i=1,...,N/2;yi=−1,i=N/2,...,N follows the balanced population assumption, which gives two label groups (+1/−1) of equal size N/2. The reordering step is introduced only after this assumption, for notational convenience in the proof. We will revise the proof to distinguish clearly between the balance assumption and the subsequent reordering, and we will clarify that this theorem is proved under a balanced group setting.
W2: The concentration and downstream-risk arguments require additional justification. Lemma G.4 assumes constant coefficients, whereas the coefficients used in Eq. E.27 are generated by attention and depend on the same noise vectors. A fixed-coefficient Gaussian argument does not directly apply; a uniform concentration result or another valid treatment is needed.
AW2: Thanks for pointing this out. The description in Lemma G.4 is not accurate for the case where the coefficients also depend on the noise vectors, and we corrected the Lemma G.4 that can be used in Equation(E.27) as follows: For ξi=∑k=1Nβi,kξk, since βi,k are bounded and ξk i.i.d follows N(0,σnoise2I), then ξi is sub Gaussian random variable. Therefore, ∥∣ξi∥∣2 is a sub-exponential random variable, and Bernstein inequality for a sub-exponential random variable can therefore be applied to it.