- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper splits MXFP4 quantization error into three parts: scale error, deadzone error and grid error. It argues that these mainly hurt gradients, rollout quality and exploration, respectively. To test this, it applies three existing techniques, one per component. Experiments use simulated W4A4 quantization during RL training on Qwen and Llama models. The combined recipe recovers most of the GSM8K drop, while transfer and long-response results still show gaps.
Critical strengths
1.Breaking the error into parts is a useful way to diagnose low-bit RL training. The additive identity is clear, and the deadzone orthogonality holds under the stated ceiling-scale rule. Measurements on three architectures give a good empirical picture of how large each part is.
2.he recovery in training quality is substantial. On Qwen2.5-3B, the combined recipe brings GSM8K from 60.1% to 81.3%, close to BF16 at 82.0% (Table 3). The Llama study uses three seeds. I also appreciate that the paper reports the harder settings where recovery fails, and says clearly that no real-hardware speedup was measured.
3.The backward-only experiment is a useful attempt to test the explanation directly. Keeping the forward and rollout quantization settings fixed, changing only the backward scale raises GSM8K accuracy from 37.7% to 72.8% on Llama (Section 4.1 and Appendix H). It is only one seed and does not prove the proposed gradient formula, but it gives a concrete reason to investigate backward quantization separately. That is more informative than only reporting the final combined recipe.
Critical weaknesses
1.The mapping from error parts to training failures is not yet justified.
- Section 4.1 treats a change of block scale as multiplying the layer output by s/s*. But changing the scale also changes which grid point each element rounds to, so the effect is not a simple multiplication.
- The gradient argument multiplies scale factors across layers, but a Transformer has normalization and residual connections in the backward pass. These can break the product form, and the paper doesn't address this.
- Appendix D.3, Eq. (23), gives a zero-mean Gaussian for a sum of Uniform[0,1) variables without subtracting their means (each has mean 1/2). The log base in Eq. (4) also needs to be stated consistently. The experiments show the recipe works. They don't show it works for the reasons given. The limitations section admits part of this, but the abstract and conclusion still make strong causal claims.
2.Some of the experimental conclusions are more certain than the evidence allows. The Qwen results use one seed, so the small remaining gaps to BF16 do not establish reliable parity. Table 4 also says seed noise cannot change the ranking against earlier methods because the full recipe has a small standard deviation. But those competing methods were run only once; the full recipe's variance tells us nothing about theirs. The large recovery over naive MXFP4 is convincing, but claims about near-BF16 performance and the exact ranking need repeated runs of the relevant baselines.
Questions for authors
1.Is the "irreducible floor" meant only as the limit when the scale goes to max|x|/6? If it is meant as a lower bound, how do you reconcile it with the 32-element example above? 2.Can you redo the gradient derivation with rounding, normalization and residual paths included, and fix the centering in Eq. (23) and the log convention in Eq. (4)? 3.Do you have interventions that change only the deadzone error, or only the grid error? If not, which claims could be narrowed to "the combined recipe helps" rather than a per-component causal story?
3 comments
Thanks for your reply. Most of my concerns are resolved, and i hope the author could add the new experimant results to the final version. I will keep my positive score.
Thank you for your positive feedback and for recognizing our revisions. We appreciate your constructive comments and are glad that our responses and new experiments have addressed most of your concerns. These new results will be added to the final version.
We thank the reviewer for the valuable comments and suggestions. We intend to keep our response short but exact. We report new measurements (App. J of the revised PDF), including where they refute our claims.
Q1. The floor. Yes. Per Eq. 3, the floor is only the limit as the scale goes to the ideal s∗=max∣x∣/6 (E8M∞). "Irreducible" means scale refinement converges to it and cannot remove it, since the E2M1 grid is fixed. OF can reduce reconstruction error below this limit by quantizing and adding back a residual in a second pass. Eq. 3 describes scale refinement for a single-pass E2M1 quantizer.
Q2. Gradient derivation. You are right, and the issue is substantive. Setup: Qwen2.5-3B, 64 held-out prompts, real backward through all 36 layers incl. norm and residual paths (App. J, Figs. 12–14).
Revision: We replace Eq. 22 with the exact blockwise expansion: Qs(Z)=Γ⊙Q∗(Z)+s⊙(ks−k∗), i.e., a scale term plus an index-correction term, composed through the actual layer Jacobians (I+JF for residual blocks). The scalar product is only a conditional approximation, and our data violate its condition. We drop the 0.18×–5.6× claim.
Eq. 23: we fix it to ∑l(δl−21)≈N(0,L/12), matching the main text at L259. Eq. 4 uses log2 throughout.
Q3. Single-component interventions. We switched each component of Def. 3.1 independently (all 8 combinations, App. J, Table 11) on a frozen checkpoint.
We narrow the claims accordingly:
Abstract, contribution 2, Sec. 4 and the conclusion will be revised.
Statistics. We agree, and will remove the Table 4 ranking sentence. New Qwen results (3 seeds, final accuracy; App. J, Table 12):
We hope that our response above has addressed your concern, and we would appreciate that you could consider to raise your rating. Thanks again for your time and effort.