2 papers
stat.ML2026
A Reverse-Gold Theorem: Positive-Data Identification by Substrate-Bounded Contrastive Learners
Rakesh Sengupta
Gold's theorem shows that no learner can identify an arbitrary language in a superfinite class from positive presentations alone. We prove a positive result of a different shape. F…
q-bio.NC2025
Lattice-Based Pruning of Recurrent Neural Networks via Poset Modeling: A Corrected Theory and a Matched-Sparsity Evaluation
Rakesh Sengupta
Magnitude pruning of recurrent neural networks (RNNs) ignores how information flows between neurons. An earlier version proposed to model RNN dependencies as a partially ordered se…