- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The authors propose Active-Subspace Noise Steering (ASNS), which shifts generative guidance in offline multi-objective optimization from the sampling trajectory to the initial noise space. Specifically, the method employs RFM to estimate the average gradient outer product (AGOP) of each objective in the noise space from proxy-evaluated noise–objective pairs, and extracts a small number of dominant sensitivity directions. For different preference weights, the method efficiently constructs the corresponding subspaces using cached cross-objective geometric information. Candidate solutions can then be generated with a single noise shift followed by one unmodified ODE sampling pass. The authors further introduce data-adaptive and Pareto-aware late-stage guidance as complementary mechanisms, and evaluate the proposed method on 47 tasks from Off-MOO-Bench, demonstrating its effectiveness and sampling efficiency.
Critical strengths
- The authors propose a novel perspective on generative guidance for offline MOO. By shifting optimization signals from step-wise trajectory guidance to the initial noise space, the paper offers a perspective distinct from existing generative approaches to offline multi-objective optimization. The overall method is structurally simple and exhibits good modularity.
- The method supports different trade-off weights through a single precomputation stage and cached cross-objective geometric information, while maintaining relatively low computational overhead.
- The paper provides substantial theoretical analysis and relatively systematic investigations of the underlying mechanisms. The experiments cover a broad range of tasks, with an overall reasonably comprehensive evaluation protocol.
Critical weaknesses
- Whether the observed spectral decay reflects intrinsic objective geometry.Although the authors show that downstream HV is robust to RFM hyperparameters, it remains unclear whether the observed spectral decay faithfully reflects the underlying noise-space objective rather than the inductive bias of the RFM estimator. I suggest directly comparing the true AGOP with the RFM-estimated AGOP on tasks where exact gradients are computationally accessible. Additionally, experiments examining the degradation of proxy accuracy would be valuable for understanding how optimization performance changes as prediction errors increase.
- The AGOP characterizes the average squared gradient magnitude. However, a direction exhibiting high sensitivity may correspond to gradients with opposite signs across different regions of the search space. Consequently, a globally fixed steering direction may not consistently improve the objective values across different samples.
- The first-order improvement characterized in Theorem 1 is essentially related to the mean gradient. Therefore, an important baseline would be to directly steer the initial noise along the estimated mean gradient. Such a comparison would help establish whether the AGOP-based active subspace provides meaningful benefits beyond simple mean-gradient steering, and thus clarify the necessity of the proposed active-subspace construction.
- Table 2 demonstrates clear sampling-time savings, but the practical importance of this speedup is under-motivated. Since the reported timing excludes training and most methods already generate 256 candidates within seconds to minutes, it would be useful to quantify when sampling becomes a meaningful fraction of the end-to-end cost, or identify applications where repeated low-latency generation is important. Otherwise, the space devoted to this efficiency argument might be better allocated to additional algorithmic analysis and ablation studies.
- Although RFM-Cone achieves the best average rank among generative methods, its overall average rank is slightly worse than MM+ICT, and its relative advantage varies considerably across task families. In light of the No Free Lunch (NFL) principle, algorithmic effectiveness is inherently dependent on the characteristics of the problem. Therefore, a more important question may be to identify the specific scenarios in which ASNS is particularly effective, as well as those in which it is less suitable, rather than emphasizing its advantages across all problems.
Questions for authors
Please refer to Weaknesses.
5 comments
Rebuttal to Reviewer v1bM continued [2/2]
W3: Mean-gradient baseline
We clarify that the AGOP is not an estimate of the mean gradient. It is the second moment of the gradient and identifies a subspace, of which the mean gradient is one direction. We ran the requested baseline at matched norm and budget: for a fixed step, the simplest instance of ASNS, it matches RFM-AN, as Thm. 1 predicts (App. B.3.1). The active subspace is necessary once the step depends on the sample, as in our guided variants: there it is provably optimal and a single mean-gradient vector cannot be used (new Prop. 2). Full results are in our reply to isuK W2, Remark 1 & Prop. 2 (App. C.3), & App. B.3.
- Fixed step (RFM-AN). By Thm. 1 the gain of a fixed step is set by the mean gradient, so it is the best fixed direction (Remark 1), and the active subspace contains it: 85–91% on C-10/MOP1 and IN-1K/MOP8, against 8–41% for a random subspace of the same rank (W1).
- Sample-dependent steps. The mean gradient keeps only what all samples share, a share of the gradient energy, 0.004–0.28 on our tasks. A step that follows each sample's gradient can use the rest: its first-order ceiling is up to higher, and among rank- subspaces the active subspace maximizes it (Prop. 2). On 120 synthetic objectives with exact gradients ( = 10–174), the per-sample step in the AGOP subspace beats the Stein shift on 119 of 120, and the AGOP subspace beats a random one on all 120. On 4 benchmark tasks, per-sample steps gain 1.2–2.2× as much as the Stein shift (App. B.3.2–B.3.3).
- Full method. RFM-APG and RFM-DAMG reshape each sample's own proxy gradient with the AGOP at every guided step, which needs the AGOP as a matrix. Both improve HV over steering alone, in 72% and 65% of task–seed pairs (App. B.4), and lower the average rank from 8.93 (RFM-AN) to 8.36 and 8.49 (Table 1).
W4: When sampling cost matters
Sampling becomes a meaningful share of the cost when a trained model is queried repeatedly. In hardware-aware NAS (our MO-NAS tasks), DC-QFA (arXiv:2604.10170, 2026) trains one supernet and then runs a hardware-constrained search for each target device's latency and memory budget. In MORL (our MO-Hopper and MO-Swimmer tasks), users specify a preference at test time and get the matching policy without retraining (Chen et al., ICLR 2026). Each device or user is a new preference query. There the gap is large: sampling costs as much as training after about 190 queries for ParetoFlow+, but not until about 3,800 for RFM-AN (App. A.4). We agree a single run is dominated by training (about 51 min on MO-Hopper).
- Each new preference. ParetoFlow+ builds each weight's next state from the offspring of its neighbouring weights, so a new preference reruns its full procedure (16.2 s on MO-Hopper). RFM-AN reuses its cache and answers in 0.8 s.
- Share of end-to-end cost spent on sampling (MO-Hopper, training included):
| Queries | ParetoFlow+: share / total | RFM-AN: share / total |
|---|---|---|
| 1 | 0.5% / 51 min | 0.8% / 51 min |
| 100 | 35% / 1.3 h | 3% / 52 min |
| 1,000 | 84% / 5.3 h | 21% / 1.1 h |
- More objectives. A fixed preference grid has 13 weights at but 6,188 at . On RE61, tracing that front takes ParetoFlow+ 2.2 min and RFM-AN 18 s, precomputation included.
W5: Where ASNS is effective
We agree, and the revision now characterizes this by two properties of the problem rather than by task: whether the data are low-dimensional, and how far the front lies from the data.
- Most effective: low-dimensional data, best solutions close to the data. The flow contracts the prior onto the data manifold (§3.1), so a few noise directions capture most of the gradient (Prop. 1) and a short step along them improves the objective (Thm. 1). MO-NAS is this case: the best architectures differ from the data by a few of 5–34 categorical choices. There RFM-Cone ranks first (C-10/MOP) and second (IN-1K/MOP) among all 18 methods.
- Regime 1: the front is far from the data. Reaching it needs a large step, and Thm. 3 shows the error grows with the step, as the flow and proxies leave the data. DTLZ and ZDT are this case, with fronts on the bounds of the design space: on ZDT4 larger steps lower HV by 15% (App. B.2.1). Surrogate-based NSGA-II searches the design space directly and has no such limit (rank 3.3 and 4.9, against 9.8 and 9.5 for RFM-Cone). Guidance closes part of the gap (App. B.4).
- Regime 2: too few dimensions to reduce. RE has and effective rank 1.4–5.5, so there is little low-rank structure to exploit and steering has no advantage over direct search (rank 9.6, against 5.7 for MM+Tri-Mentor).
In both regimes ASNS trails direct surrogate search but stays best or on par among generative methods (rank 9.6 vs 13.0 for PCD on RE). On MORL the limit is proxy accuracy, not geometry (reply to isuK Q4).
Thanks for your review!
Dear Reviewer v1bM,
As the rebuttal period comes to an end, we wanted to thank you for taking the time to read our work. We would also like to follow up on our rebuttal response and ask whether we were able to address all of your questions. Additionally, we have also posted a summary comment for all reviewers that lists where each change appears in the revised PDF. We would be happy to address any remaining concerns!
We thank the reviewer for their helpful comments and questions! We address them all below [1/2].
W1: Is the spectral decay intrinsic?
We ran both suggested experiments (new App. B.2.7–B.2.8). (1) The exact AGOP is already low-rank, so the decay is a property of the noise-space objective and not of the inductive bias of the RFM estimator. (2) HV is stable when the proxies are retrained on 50% and 25% of the data, even where proxy accuracy drops most (see reply to isuK Q4).
Exact vs RFM AGOP. On 3 tasks we computed the exact AGOP by differentiating through the full ODE solve at 5,000 fresh noises (5 seeds). D is the dimension of the representation the flow is trained on, and the participation ratio is (∑jλj)2/∑jλj2.
Proxy degradation (App. B.2.8). To understand how performance changes as prediction errors increase, we first bound it and then test it.
W2: Opposite signs
We now measure it directly (new App. B.3.4): the single global ASNS step still improves most samples, 73% to 100% of candidates on 6 tasks. We agree that gradients along a single direction can have opposite signs, and Thm. 1 already accounts for it. E.g., for H(z)=z12 the gradient 2z1 has opposite signs on the two halves of the noise, so the mean gradient is 0 while the AGOP is 4. ASNS handles such directions in two ways.
Fixed step. Alg. 1 gives each direction the sign of its mean derivative dˉj (Pearson sign, §3.3), and in Thm. 1 the gain is set by dˉj, not by λj. A direction whose gradients cancel has dˉj≈0 and adds nothing (reversing the leading direction lowers the true objective, App. B.2.9, Fig. 9), so the gain comes from the directions with a consistent sign. Cancellation is real: the sign-consistent share cj=(uj⊤E∇Hw)2/λj is about 10−3 for the top 10 directions on C-10/MOP1 and IN-1K/MOP8 (it is energy-weighted, so a few large opposing gradients can dominate it). Yet, decoding the same noise with and without the step (5 seeds), the true scalarized objective improves for most candidates, i.e. the step improves samples consistently:
Mean gain is positive on every task, and the consistency holds at every step size tested: on IN-1K/MOP8, 79% of candidates already improve at a tenth of the default step.
Sample-dependent steps. Where signs do flip, a sample whose gradient opposes the fixed step is not improved by it. Each sample must follow its own gradient, which our guided variants do (§4). This needs the AGOP: in the example above the mean gradient gives no direction, while the AGOP still identifies z1. RFM-Cone also resolves conflicts between objectives, decreasing none to first order (Thm. 2). See W3, which quantifies how much such steps gain.