arXiv AI
Constrained Hyperparameter Optimization for Streaming Data
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 21
Bilevel Optimization of Topology and Hyperparameters (BOTH)
The paper introduces BOTH, a method that differentiates topology optimization (TO) itself to compute hypergradients for tuning hyperparameters alongside the primary design optimization. By evaluating only one or two TO steps, the approach provides sufficient information and scales to thousands of hyperparameters with a cost comparable to a few standard TO runs. Experiments on stress‑constrained and compliance problems, including a neural‑parameterized density field, demonstrate the effectiveness of this joint optimization strategy.
arXiv Machine Learning
Sep 16
Learning efficient representations of complex constraints for scalable optimization
The paper introduces PolyFormer, a physics-informed machine learning framework that learns compact polytopic representations of complex constraints. By transforming constraint-induced geometry into efficient polytopic reformulations, PolyFormer reduces optimization complexity and enables the use of standard solvers. Evaluations on large‑scale resource aggregation, network‑constrained optimization, and uncertainty‑aware optimization show up to 6,400‑fold speedups and 99.87% memory savings while keeping feasibility and objective errors low.
arXiv AI
Jul 28
Constraint-Bound Agnostic Bayesian Optimization: One Model for All Thresholds
arXiv:2607. 23448v1 Announce Type: cross Abstract: Expensive constrained optimization problems in real-world industry design often involve constraint thresholds that are difficult to determine in advance.
arXiv AI
Sep 2
Rethinking Learnability in Offline Data-driven Optimization
arXiv:2609.01493v1 Announce Type: cross Abstract: Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-w...
arXiv AI
Jul 21
SEER: Supervised Learning to Control Energetic Reasoning
arXiv:2607. 16523v1 Announce Type: new Abstract: One of the main strengths of Constraint Programming is the ability to reduce the search space via propagation.
arXiv Machine Learning
Jun 19
DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
arXiv:2605. 30456v2 Announce Type: replace Abstract: Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches.