SyncAI.news, a Varaisys broadcasting
Differentiable Exact Learning
HP

Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion

· 1 min read

ResearcharXiv cs.AI

Differentiable Exact Learning

arXiv:2611.21486v1 Announce Type: cross Abstract: We introduce a framework for differentiable exact learning that couples an unbounded external environment to a state-tracking neural controller, which we train on policy-trajectory observations (PTOs): expert behavior traces that expose observations and actions while hiding internal states. In addition to the learning framework, we introduce Differentiable Finite-State Transducers (DFSTs) which use multilinear updates, support log-parallel training, and emulate arbitrary finite-state controllers, yielding computational universality through environmental interaction. From tiny training datasets, compact DFSTs achieve extreme length generalization on arithmetic and universal-simulation tasks. We replicate the success of DFSTs on RNNs and GRUs, thereby supporting a broader learning recipe: State-Tracking Controller + Unbounded External Environment + PTOs = Extreme Length Generalization. Beyond length generalization, our metric-extraction protocol recovers interpretable discrete controllers from trained DFSTs, which we prove equivalent to the target arithmetic and universal-simulation algorithms. Furthermore, for our Softmax DFST models, simply taking $\mathrm{argmax}$ over the transition probabilities yields discrete controllers which provably exactly perform universal Turing-machine simulation and binary arithmetic. Proving exact learning for the neural controllers requires assumptions, which we empirically support. We make our code, training recipes, model weights, and proof checkers publicly available at https://github.com/fanagor/DEL.

Original source

This story was published by arXiv cs.AI and written by Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News