# NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces

arXiv: https://arxiv.org/abs/2602.03901 · HTML: https://mlsanity.com/paper/2602.03901/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2006.05078/) (2020)
- [Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement](https://mlsanity.com/paper/2105.08195/) (2021)
- [Masksembles for Uncertainty Estimation](https://mlsanity.com/paper/2012.08334/) (2020)
- [Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces](https://mlsanity.com/paper/2109.10964/) (2021)
- [Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimization](https://mlsanity.com/paper/2210.01628/) (2022)
- [RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels](https://mlsanity.com/paper/2310.03912/) (2023)
- [Bayesian Optimization of Function Networks with Partial Evaluations](https://mlsanity.com/paper/2311.02146/) (2023)
- [Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models](https://mlsanity.com/paper/2405.08674/) (2024)
- [Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling](https://mlsanity.com/paper/2412.08776/) (2024)
- [NeuroLGP-SM: A Surrogate-assisted Neuroevolution Approach using Linear Genetic Programming](https://mlsanity.com/paper/2403.19459/) (2024)
- [Amortized Variational Inference for Deep Gaussian Processes](https://mlsanity.com/paper/2409.12301/) (2024)
- [Sparse Gaussian Neural Processes](https://mlsanity.com/paper/2504.01650/) (2025)
- [Rank-Based Learning and Local Model Based Evolutionary Algorithm for High-Dimensional Expensive Multi-Objective Problems](https://mlsanity.com/paper/2304.09444/) (2023)
- [Permutation-based multi-objective evolutionary feature selection for high-dimensional data](https://mlsanity.com/paper/2501.14310/) (2025)
- [Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification](https://mlsanity.com/paper/2505.15671/) (2025)

## Built on by (most cited first, 1 of 1)

- [Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS](https://mlsanity.com/paper/2604.10734/) (2026)

## Abstract (arXiv)

The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.