20 citations · 33 across the 7 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
The Null Is the Hard Part: Exact Tests for Memorization in Generative Models
Sushovan Majhi, Pramita Bagchi
Memorization audits of generative models read similarity scores against thresholds, with no null distribution, and the conclusions they support can be wrong. By MemBench's rule, th…
cs.LG2026
COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules
Sushovan Majhi, Atish Mitra, Žiga Virk +1
Every multiparameter persistence vectorization we know of carries a one-sided Lipschitz upper bound and nothing below it: without a lower gauge there is no sense in which the featu…
cs.LG2026
A Closed-Form Adaptive-Landmark Kernel for Certified Point-Cloud and Graph Classification
Sushovan Majhi, Atish Mitra, Žiga Virk +1
We introduce PALACE (Persistence Adaptive-Landmark Analytic Classification Engine), the data-adaptive companion to PLACE, paying a small cross-validation tier on three knobs (budge…