Search papers, labs, and topics across Lattice.
University of Cambridge
2
0
3
Adding uninformative ambient dimensions completely breaks kurtosis-based projection pursuit, proving that high-order unsupervised discovery fundamentally requires second-order subspace pre-filtering to avoid hallucinating structure in pure Gaussian noise.
By jointly inferring model parameters and learning unknown dynamics across related systems, this work offers a more complete picture of complex physical systems where detailed properties and complete laws are unknown.
