Tag
This paper proposes a nonparametric variational learning framework to simultaneously infer interaction kernels and environmental forces in collective dynamics, validated on benchmark models with a model-selection procedure.
This paper introduces a low-rank degree-two density projection method for nonparametric changepoint detection in high dimensions, using matrix mean estimation to handle distributional changes without parametric assumptions.
This paper proves that task-relevant latent representations can be identified from generalist models in a fully nonparametric setting without interventions or parametric constraints, achieving a hierarchical identifiability guarantee across time steps and within each step.
This paper establishes nonparametric identifiability guarantees for extracting task-relevant representations from generalist models, proving that task structure is identifiable across time steps and latent representations are identifiable within each step under sparsity regularization.