15 citations · 34 across the 26 of their papers we have counts for
7 papers · 1 filter
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…
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…
Certified Topological Interaction in Neural Representations: Exact Tests and the Statistic They Require
Sushovan Majhi
Class disentanglement--the separation of a representation's class-conditional point clouds along depth and over training--is measured by descriptive curves: the sentence such a stu…
A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification
Sushovan Majhi, Atish Mitra, Žiga Virk +1
We introduce PLACE (Persistence-Landmark Analytic Classification Engine), a closed-form pipeline for classifying point clouds and graphs through their persistent-homology signature…
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…
Topological Characterization of Churn Flow and Unsupervised Correction to the Wu Flow-Regime Map in Small-Diameter Vertical Pipes
Brady Koenig, Sushovan Majhi, Atish Mitra +2
Churn flow-the chaotic, oscillatory regime in vertical two-phase flow-has lacked a quantitative mathematical definition for over years. We introduce the first topology-based c…
Interpretable Classification of Time Series Using Euler Characteristic Surfaces
Salam Rabindrajit Luwang, Sushovan Majhi, Vishal Mandal +3
Persistent homology (PH) -- the conventional method in topological data analysis -- is computationally expensive, requires further vectorization of its signatures before machine le…