For wide two-layer linearized neural policies in deterministic continuous RL, the locally attainable states concentrate on a manifold of dimension at most 2da+1, independent of the state dimension.
Efficient Representation of Low-Dimensional Manifolds using Deep Networks
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space. We show that deep networks can efficiently extract the intrinsic, low-dimensional coordinates of such data. We first show that the first two layers of a deep network can exactly embed points lying on a monotonic chain, a special type of piecewise linear manifold, mapping them to a low-dimensional Euclidean space. Remarkably, the network can do this using an almost optimal number of parameters. We also show that this network projects nearby points onto the manifold and then embeds them with little error. We then extend these results to more general manifolds.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
For wide two-layer linearized neural policies in deterministic continuous RL, the locally attainable states concentrate on a manifold of dimension at most 2da+1, independent of the state dimension.