arXiv Machine Learning
Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 21
Physical-Support Confidence Sets for Highly Coherent Dictionaries
arXiv:2608. 20295v1 Announce Type: new Abstract: Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for highly coherent dictionaries where alternative calibration-compatible dictionaries may assign different physical meanings to the same selected support.
arXiv Machine Learning
Jun 2
How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations
arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.
arXiv Machine Learning
Jun 4
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
arXiv:2606. 04100v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) enable efficient and accurate atomistic simulations but depend critically on the quality and diversity of the training data.
arXiv Machine Learning
Jul 16
Multi-Dictionary Learning for Low Rank Sparse Coding
arXiv:2509. 10033v2 Announce Type: replace Abstract: Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms.
arXiv Machine Learning
Sep 18
Truncated automatic sparse differentiation for machine learning interatomic potentials
The paper introduces truncated automatic sparse differentiation (ASD) to efficiently compute higher‑order derivatives, such as Hessians, for machine learning interatomic potentials (MLIPs). By exploiting the locality of atomic interactions, ASD identifies a sparsity pattern that allows exact Hessian calculation for large porous materials, while truncated ASD discards distant, small Hessian entries to achieve order‑of‑magnitude speedups with minimal loss in predictive accuracy. The authors demonstrate these methods on several foundational MLIPs, showing modest speedups for full ASD and significant gains for the truncated approach.
arXiv Machine Learning
Aug 17
Variation Brownian Kernel Ladders
arXiv:2608. 13882v1 Announce Type: new Abstract: Claims about the benefit of depth depend on the complexity assigned to a representation.