3 papers
cs.CC2026
Algorithmic Information Bounds for Distances and Orthogonal Projections
Peter Cholak, Marianna Csörnyei, Neil Lutz +3
We introduce a new technique for proving bounds on the Kolmogorov complexity of geometric objects in Euclidean space, such as points and lines. We apply this technique to prove two…
cs.LG2026
Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
Patrick Lutz, Themistoklis Haris, Arjun Chandra +2
Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the h…
math.CA2025
Bounding the dimension of exceptional sets for orthogonal projections
Peter Cholak, Marianna Csornyei, Neil Lutz +3
It is well known that if is an analytic set of Hausdorff dimension , then for a.e.\ , where denotes…