Advancing Optimal Subset Oracle via Learning Relaxation of Neural Set Functions

arXiv:2607.11555 · cs.LG · Submitted 2026-07-13 · Read on arXiv

cs.LG

Submitted: 2026-07-13

Updated: 2026-09-30

Code: https://github.com/shaohua0116/MultiDigitMNIST

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Computational overhead — 2× in this paper · explained in 2 episodes

Sources

• Deep Submodular Functions
• Energy-Based Transformers are Scalable Learners and Thinkers
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• FEAT: Free energy Estimators with Adaptive Transport
• SGDR: Stochastic Gradient Descent with Warm Restarts
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks