TAMO is a transformer policy pretrained with RL to perform amortized multi-objective optimization in-context, delivering 50-1000x faster proposals while matching Pareto quality on benchmarks.
Reinforced in-context black-box optimization.arXiv preprint arXiv:2402.17423, 2024a
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
SemanticOpt fine-tunes LLMs on structured Bayesian optimization trajectories augmented with natural-language context to jointly use numerical and semantic evidence for black-box optimization.
citing papers explorer
-
In-Context Multi-Objective Optimization
TAMO is a transformer policy pretrained with RL to perform amortized multi-objective optimization in-context, delivering 50-1000x faster proposals while matching Pareto quality on benchmarks.
-
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
-
SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization
SemanticOpt fine-tunes LLMs on structured Bayesian optimization trajectories augmented with natural-language context to jointly use numerical and semantic evidence for black-box optimization.