Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
cs.LG
Submitted: 2025-09-02
Updated: 2026-11-13
Terminology
Sources
- Pathologies of Predictive Diversity in Deep Ensembles
- Deep Ensembles: A Loss Landscape Perspective
- Distilling the Knowledge in a Neural Network
- Distribution Preserving Multiple Hypotheses Prediction for Uncertainty Modeling
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis