The paper introduces NN‑linkage, a neural network model that learns task‑specific merge rules for hierarchical clustering while preserving the recursive structure and efficiency of classical linkage algorithms. It aligns with the Lance‑Williams recurrence, enabling it to approximate any continuous linkage function and even implement symmetric constant‑coefficient LW recurrences exactly. Experiments on clock‑tree routing and phylogenetic reconstruction show that NN‑linkage outperforms both traditional linkage methods and other neural approaches, extending efficient hierarchical clustering to new scientific and engineering tasks.
Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from tracking pathogen spread to reconstructing the history o...
arXiv:2607. 18311v1 Announce Type: cross Abstract: Comparing phylogenetic tree topologies is essential for understanding epidemic dynamics, yet biologically meaningful distances such as the Subtree Prune and Regraft (SPR) distance are NP-hard to compute and intractable on large datasets.
arXiv:2610.19053v1 Announce Type: new Abstract: Inference of phylogenetic trees from sequences plays a central role in understanding evolutionary relationships, with applications ranging from trackin...
arXiv:2606. 11646v1 Announce Type: new Abstract: Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics.
arXiv:2606. 21497v2 Announce Type: replace-cross Abstract: Modern deep neural networks are trained using error backpropagation, which requires sequential forward and backward computations across network layers.
Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics. The features in these data often come with known hierarchical structure (e.
arXiv:2607. 28954v1 Announce Type: new Abstract: Branch and Bound (BaB) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems.
arXiv:2404. 03082v3 Announce Type: replace Abstract: Partially ordered sets (posets) are discrete mathematical structures that formalize the notion of comparison without forcing every pair of objects to be comparable.
arXiv:2602. 15649v2 Announce Type: replace Abstract: In dynamical systems reconstruction (DSR) we aim to recover the dynamical system (DS) underlying observed time series.
arXiv:2606. 09924v1 Announce Type: cross Abstract: Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input.
arXiv:2602. 22422v2 Announce Type: replace-cross Abstract: Smooth-basis models such as Chebyshev polynomial regressors and radial basis function (RBF) networks are well established in numerical analysis.
arXiv:2511. 04124v3 Announce Type: replace Abstract: Symbolic regression (SR) models complex systems by discovering mathematical expressions that capture underlying relationships in observed data.