REVIEW 5 cited by
On the Limitations of Representing Functions on Sets
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed as the cardinality of the sets under consideration increases. However, we demonstrate that the analysis leading to this conjecture requires mappings which are highly discontinuous and argue that this is only of limited practical use. Motivated by this observation, we prove that an implementation of this model via continuous mappings (as provided by e.g. neural networks or Gaussian processes) actually imposes a constraint on the dimensionality of the latent space. Practical universal function representation for set inputs can only be achieved with a latent dimension at least the size of the maximum number of input elements.
Forward citations
Cited by 5 Pith papers
-
Meson-Nucleus Bound States with Neural-Network Quantum States
Neural-network quantum states applied to HAL QCD meson-nucleon potentials predict bound states for phi at A>=2, J/psi at A>=4, and eta_c at A>=6, with binding energies from tens of MeV to sub-MeV scales.
-
Medium-mass nuclei with neural quantum states
Pfaffian-Jastrow neural quantum states yield ground-state energies and charge radii for nuclei up to A=58, with weak p-wave terms reducing average energy error to ~3% while revealing Hamiltonian sensitivity and A^3 scaling.
-
Revisiting the Volume Hypothesis
The generalization advantage of SGD over random sampling diminishes with growing training set size in binary networks, as measured by joint density of states over train and test accuracy.
-
Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning
SCP ranks and prunes context sentences using Shapley values from a learned Deep Sets value function, matching or beating baselines on several multi-hop QA datasets at 50% compression.
-
Hypernuclei with Neural Network Quantum States
Neural network quantum states, extended to include Lambda hyperons, reproduce hypernuclear separation energies to within roughly 9% and predict the observed proton-radius shrinkage in 7ΛLi.
Discussion (0). Sign in to comment.