arXiv AI June 30, 2026 By Abhishek Shukla, Ankur Sinha, Faiz Hamid

Bilevel Optimization for Neural Architecture Search

arXiv:2606. 29582v1 Announce Type: cross Abstract: Bilevel optimization has become an influential and widely adopted framework for addressing hierarchical optimization problems in machine learning, providing an effective approach to modeling the interaction between two levels of optimization, with applications such as hyperparameter tuning, meta-learning, adversarial training, and data poisoning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 17

Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

arXiv:2608. 14443v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss.

By Abhishek Shukla, Ankur Sinha, Faiz Hamid

llms

arXiv AI

Aug 17

LP-NAS: Linear Programming-based Neural Architecture Search

arXiv:2608. 14472v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise.

By Abhishek Shukla, Ankur Sinha, Faiz Hamid

arXiv AI

Sep 23

Artificial Neural Networks as Surrogate Models in Black Box Optimization

arXiv:2609.22329v1 Announce Type: cross Abstract: Black-Box Optimization (BBO) is often applied in several engineering fields and can utilize an advancement of numerical measure- ments and simulation...

By Md Khadimul Islam Zim (Czech Academy of Sciences, Institute of Computer Science, Prague, Czech Republic), Martin Hole\v{n}a (Czech Academy of Sciences, Institute of Computer Science, Prague, Czech Republic)

benchmarks

arXiv Machine Learning

Aug 14

Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level

arXiv:2608. 12704v1 Announce Type: cross Abstract: Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning.

By Yicong Jiang, Feihu Huang

arXiv Machine Learning

Jun 2

Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA

arXiv:2606. 00862v1 Announce Type: cross Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems.

By Xiao Jin, Yongxiong Wang, Haobo Liu, Yudong Du, Yukun Du

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 9

Efficient Long-Horizon Learning for Learned Optimization

arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.

By Xiaolong Huang, Benjamin Th\'erien, James Harrison, Eugene Belilovsky

llms computer-vision

One email a morning, machine-written

Related stories

Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

LP-NAS: Linear Programming-based Neural Architecture Search

Artificial Neural Networks as Surrogate Models in Black Box Optimization

Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level

Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA

Efficient Long-Horizon Learning for Learned Optimization