3 papers
cs.LG2026
Bounded Precision-Geometry Scaling for Robust Multi-Task Learning under Loss Scale Mismatch
Krishna Subedi
Multi-task learning often combines losses that span several orders of magnitude, causing homoscedastic uncertainty weighting to degrade severely. We propose Bounded Precision-Geome…
cs.AI2026
Uniform Herding: Exemplar Replay with Representation Refresh
Krishna Subedi
As the feature representation changes, replay must preserve the earlier classes. However, only a bounded active exemplar set can be replayed. We propose Uniform Herding, which allo…
cs.PF2026
Reflected UAS: Corrected Deterministic Stability and Direct CTMC Drift Calculation
Krishna Subedi
We analyze Reflected UAS routing for heterogeneous multi-server queues at fixed parameters under subcritical load. The deterministic surrogate is a reflected ODE on the nonnegative…