# Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design

arXiv: https://arxiv.org/abs/2602.03319 · HTML: https://mlsanity.com/paper/2602.03319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 72 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [Max-value Entropy Search for Efficient Bayesian Optimization](https://mlsanity.com/paper/1703.01968/) (2017)
- [Predictive Entropy Search for Efficient Global Optimization of Black-box Functions](https://mlsanity.com/paper/1406.2541/) (2014)
- [Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2006.05078/) (2020)
- [A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization](https://mlsanity.com/paper/2111.05040/) (2021)
- [GIBBON: General-purpose Information-Based Bayesian OptimisatioN](https://mlsanity.com/paper/2102.03324/) (2021)
- [Data-driven discovery of intrinsic dynamics](https://mlsanity.com/paper/2108.05928/) (2021)
- [Learning to Weight Samples for Dynamic Early-exiting Networks](https://mlsanity.com/paper/2209.08310/) (2022)
- [Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints](https://mlsanity.com/paper/2402.07692/) (2024)
- [Sample-Efficient Optimisation with Probabilistic Transformer Surrogates](https://mlsanity.com/paper/2205.13902/) (2022)

## Abstract (arXiv)

Target-oriented discovery under limited evaluation budgets requires making reliable progress in high-dimensional, heterogeneous design spaces where each new measurement is costly, whether experimental or high-fidelity simulation. We present an information-theoretic framework for target-oriented adaptive sampling that reframes optimization as trajectory discovery: instead of approximating the full response surface, the method maintains and refines a low-entropy information state that concentrates search on target-relevant directions. The approach couples data, model beliefs, and physics/structure priors through dimension-aware information budgeting, adaptive bootstrapped distillation over a heterogeneous surrogate reservoir, and structure-aware candidate manifold analysis with Kalman-inspired multi-model fusion to balance consensus-driven exploitation and disagreement-driven exploration. Evaluated under a single unified protocol without dataset-specific tuning, the framework improves sample efficiency and reliability across 14 single- and multi-objective materials design tasks spanning candidate pools from 600 to 4 × 106 and feature dimensions from 10 to 103, typically reaching top-performing regions within 100 evaluations. Complementary 20-dimensional synthetic benchmarks (Ackley, Rastrigin, Schwefel) further demonstrate robustness to rugged and multimodal landscapes.