Author

S. Kargaran

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions

A soft state representation assigns each state a vector of nonnegative class weights that sum to one, which jointly determine the accuracy of linear prediction and distinguishes agreement with reconstruction classes, attainable prediction accuracy, and exact operator closure.

Mohit Kumar, S. Kargaran · 0 citations

#artificial intelligence Preprint Sep 2026

Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions

We study when geometry-induced soft state abstractions admit accurate finite-dimensional linear dynamics. Each state is represented by simplex-valued coordinates obtained from class-specific Kernel Affine Hull Machine (KAHM) reconstruction scores, and a matrix is used to predict the next-state coordinates. Our main res...

Mohit Kumar, S. Kargaran · 0 citations