Introduces the directional linear separability measure (LSM) as an asymmetric diagnostic for one-sided affine separability of neural representations.
Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
MoE Top-k routing equals the k-th elementary symmetric tropical polynomial, making sparsity combinatorial depth that scales capacity by binom(N,k) and gives MoE combinatorial resilience on manifolds.
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.
Thesis uses statistical mechanics to study DAM and RBM models for understanding memorization, low-dimensional learning, and adversarial robustness in neural networks.
citing papers explorer
-
Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning
NoFA-BC proposes a non-forgetting allocator using recursive least-squares and bi-level competition for improved knowledge allocation in class-incremental learning.