- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes ICPSL, a Transformer hypernetwork pretrained on synthetic GP-sampled multi-objective problems. Given a small offline dataset, it generates the weights of a preference-conditioned MLP in one forward pass. The MLP outputs a latent-conditioned mixture of logit-normal distributions over solutions, trained with a Tchebycheff free-energy (KL-to-Gibbs) objective.
Critical strengths
- The two-level amortization (across preferences and across problems) is clearly presented.
- Objective-based pretraining removes the need for Pareto-optimal labels.
Critical weaknesses
- The empirical claims are not supported, especially on real-world problems. In Tables 5–7, no ICPSL variant achieves the best HV on RE23, RE24, or RE32 under any context distribution (0/9). ParetoFlow or DOMOO is best in every case. Meanwhile, all of ICPSL-MM's 15 wins come from low-dimensional () synthetic functions.
- Prior–target mismatch is not analyzed. The prior draws each objective independently, with no control over the degree of conflict between objectives. The paper does not analyze how this prior–target mismatch affects performance, which may explain the RE results.
- Ablations are missing. No component is ablated: the Tchebycheff signature embedding versus raw objectives , the size of the reference preference bank, the low-rank decoder, the encoder depth, the temperature , or the prior design (kernel mixture, ARD length-scale range).
- Novelty is limited. The framework combines prior-data hypernetwork pretraining (Müller et al., 2025), preference-conditioned Pareto set learning and hypernetworks (Navon et al., 2021; Lin et al., 2022), and synthetic-GP pretraining for multi-objective optimization (Zhang et al., 2026).
References
Xi Lin, Zhiyuan Yang, Xiaoyuan Zhang, and Qingfu Zhang. Pareto set learning for expensive multi-objective optimization. In Advances in Neural Information Processing Systems, volume 35, pp. 19231–19247, 2022.
Andreas C. Müller, Carlo Curino, and Raghu Ramakrishnan. MotherNet: Fast training and inference via hyper-network transformers. In International Conference on Learning Representations, 2025.
Aviv Navon, Aviv Shamsian, Gal Chechik, and Ethan Fetaya. Learning the Pareto front with hypernetworks. In International Conference on Learning Representations, 2021.
Xinyu Zhang, Conor Hassan, Julien Martinelli, Daolang Huang, and Samuel Kaski. In-context multi-objective optimization. In International Conference on Learning Representations, 2026.
Questions for authors
Please see weaknesses.
2 comments
3. Prior–target mismatch.
Thank you for raising this concern. Sampling objective functions independently does not imply that their optima are aligned or that the resulting problems lack conflict. The objectives share the same decision space and can favor different solution regions, producing trade-offs during pretraining. Independent draws from the GP prior allow us to generate a large and diverse collection of training problems, supporting generalization to unseen tasks. Restricting the objectives to prescribed conflict patterns would constrain the allowable function combinations and could reduce this diversity. We therefore adopt independent sampling to encourage broad exposure to different objective landscapes and trade-off structures.
To provide additional analysis on prior–target mismatch, we examine transfer under a controlled extreme example involving objectives with substantially different regularity from the GP prior, as described below. This experiment complements the discussion of objective conflict by testing another important aspect of prior mismatch. We construct the Weierstrass–Takagi multi-objective problem (WTMOP), using Weierstrass [1] and Takagi [2] functions as its two objectives. These functions are continuous but extremely non-smooth, deliberately violating the smoothness of the mixed kernels during training. We use the domain [0,0.5] to ensure clear conflict between the two objectives.
Moreover, the functions have a strict Hölder exponent guarantee with controllable parameters. The Hölder exponent measures the local roughness of a function [3,4]. A larger indicates a smoother function. For Weierstrass, the , we set , and . For Takagi, . The sample paths of a Matern- GP have almost-Hölder exponent . The table below compares these Hölder exponents, highlighting the smoothness mismatch between the Weierstrass-Takagi functions and our pretraining distribution.
| Function / Kernel | Weierstrass | Takagi | Matérn-3/2 | Matérn-5/2 | RBF |
|---|---|---|---|---|---|
| 0.325 | 1.0 | 1.5 | 2.5 |
We evaluate the pretrained model in our paper using ten-observation contexts. The table reports PSQ ranks under LHS, Sobol, and uniform sampling.
| Algorithm | LHS | Sobol | Uniform | Overall | Wins | Top-3 cases |
|---|---|---|---|---|---|---|
| ParetoFlow | 5.00 | 5.00 | 6.00 | 5.33 | 0/3 | 0/3 |
| PSLR | 8.00 | 8.00 | 8.00 | 8.00 | 0/3 | 0/3 |
| PSLO | 7.00 | 7.00 | 7.00 | 7.00 | 0/3 | 0/3 |
| DOMOO | 6.00 | 6.00 | 4.00 | 5.33 | 0/3 | 0/3 |
| PFNs4BO | 1.00 | 2.00 | 1.00 | 1.33 | 2/3 | 3/3 |
| ICPSL-MAP | 4.00 | 4.00 | 5.00 | 4.33 | 0/3 | 0/3 |
| ICPSL-CAM | 2.00 | 1.00 | 2.00 | 1.67 | 1/3 | 3/3 |
| ICPSL-MM | 3.00 | 3.00 | 3.00 | 3.00 | 0/3 | 3/3 |
The results show that ICPSL retains competitive preference-conditioned solution quality under this pronounced prior mismatch. CAM outperforms ParetoFlow, PSLR, PSLO, and DOMOO under every context distribution, achieving the best PSQ under Sobol sampling and the second-best under LHS and uniform sampling. MM consistently ranks third. This extreme example suggests that the model can transfer useful information learned during GP pretraining to objectives with substantially different regularity.
[1] Hardy, Godefroy Harold. Weierstrass’s non-differentiable function.
[2] Takagi, Teiji. A simple example of the continuous function without derivative.
[3] Evans, Lawrence C. Partial differential equations.
[4] Gilbarg, David, et al. Elliptic partial differential equations of second order.
4. Novelty clarification.
Thank you for raising this concern. The key contribution of ICPSL is learning to construct a reusable preference-conditioned solution model from an unseen problem’s offline observations in a single forward pass. MotherNet generates classifiers from labeled datasets, existing PSL methods train a solution model for each problem, and TAMO learns a policy for sequential optimization without explicitly modeling the preference–solution structure. ICPSL instead learns how offline observations determine an entire preference-conditioned solution model, amortizing both model construction across problems and solution search across preferences. This capability is relevant to many real-world applications where observations are scarce and decision-makers need to explore different preferences. After synthetic pretraining, ICPSL constructs a solution model without problem-specific parameter updates and answers new preference queries without repeated optimization. This reduces the computational cost of deploying solution models across new problem instances and enables rapid exploration of alternative trade-offs. We will clarify these distinctions and highlight the practical value of our contribution.
We thank the reviewer for the constructive comments and suggestions. We respond to each point below.
1. Empirical claims on real-world problems.
Thank you for raising this concern. We agree that Tables 5–7 do not establish HV superiority on the RE problems. Our motivation is to construct a reusable preference-conditioned solution model from sparse offline observations while avoiding costly problem-specific training and repeated preference-wise search. We will clarify that the engineering results support a quality–efficiency trade-off rather than consistent HV superiority.
2. Ablation studies.
Thank you for raising this question. We have added ablation studies by pretraining separate models with different context embeddings, reference preference bank sizes, and ARD length-scale ranges. Following the suggestions raised by Reviewers 8s3L and AgHE about the preference-aligned performance metric, we evaluate these variants using preference-conditioned solution quality (PSQ), defined as the average Tchebycheff value of each predicted solution under its corresponding query preference, which better aligns with query-specific solution quality than HV: PSQ=T1∑q=1Tmaxj=1,…,mλqj fj!(x^(λq)). Intuitively, lower PSQ indicates better solution quality for the queried preferences. The table reports relative changes from the corresponding default setting: Change( where GM denotes the geometric mean, PSQ is the mean over independent trials and c indexes matched problem–sampler cases. Negative values indicate improvement.
The results show that the Tchebycheff signature achieves better PSQ than raw objective inputs under all three inference strategies. This indicates that explicitly representing observation quality across reference trade-offs helps the model infer solutions for queried preferences. Increasing the reference bank size improves PSQ across the three strategies, suggesting that denser trade-off information can refine the context representation. The length-scale ablation suggests that emphasizing more gradually varying objective landscapes during pretraining improves transfer to the evaluated benchmarks. With only a small offline context, such regularity may make the underlying objective structure easier to infer. This highlights the importance of the landscape geometry represented during pretraining and suggests scope for improving prior–target matching.
The low-rank decoder used in our paper keeps GPU memory requirements manageable during pretraining. Generating full-rank hidden-layer weights would sharply increase memory usage, making pretraining infeasible on our available hardware. For encoder depth, we adopt the default 12-layer Transformer encoder used in PFN-based methods. Our comparison with PFNs4BO is reported in Section 1 of our response to Reviewer AgHE. The temperature τ controls the balance between low Tchebycheff energy and distributional entropy. We set τ=0.015 to favor low-energy solutions while retaining entropy regularization against premature concentration. This value is fixed across target problems without task-specific tuning.