3 papers
cs.LG2024
On Reductions and Representations of Learning Problems in Euclidean Spaces
Bogdan Chornomaz, Shay Moran, Tom Waknine
Many practical prediction algorithms represent inputs in Euclidean space and replace the discrete 0/1 classification loss with a real-valued surrogate loss, effectively reducing cl…
cs.LG2023
Local Borsuk-Ulam, Stability, and Replicability
Zachary Chase, Bogdan Chornomaz, Shay Moran +1
We use and adapt the Borsuk-Ulam Theorem from topology to derive limitations on list-replicable and globally stable learning algorithms. We further demonstrate the applicability of…
math.GR2023
Quasilinear Emulation of Turing Machines by S-machines
Bogdan Chornomaz, Francis Wagner
We prove that for any , a non-deterministic Turing machine with time complexity can be emulated by an -machine with time and space complexiti…