Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization
cs.LG, cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- Measuring and regularizing networks in function space
- Efficient Lifelong Learning with A-GEM
- Approximation Methods for Bilevel Programming
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
- Variational Continual Learning
- Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
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