no code implementations • 22 Mar 2023 • Vikas C. Raykar, Arindam Jati, Sumanta Mukherjee, Nupur Aggarwal, Kanthi Sarpatwar, Giridhar Ganapavarapu, Roman Vaculin
The explanations are in terms of the SHAP values obtained by applying the TreeSHAP algorithm on a surrogate model that learns a mapping between the interpretable feature space and the forecast of the black-box model.
no code implementations • 7 Jul 2022 • Ehud Aharoni, Moran Baruch, Pradip Bose, Alper Buyuktosunoglu, Nir Drucker, Subhankar Pal, Tomer Pelleg, Kanthi Sarpatwar, Hayim Shaul, Omri Soceanu, Roman Vaculin
In this work, we propose a novel set of pruning methods that reduce the latency and memory requirement, thus bringing the effectiveness of plaintext pruning methods to HE.
no code implementations • 5 Mar 2021 • Kanthi Sarpatwar, Karthik Nandakumar, Nalini Ratha, James Rayfield, Karthikeyan Shanmugam, Sharath Pankanti, Roman Vaculin
In this work, we propose a framework to transfer knowledge extracted by complex decision tree ensembles to shallow neural networks (referred to as DTNets) that are highly conducive to encrypted inference.
no code implementations • NeurIPS 2019 • Kanthi Sarpatwar, Karthikeyan Shanmugam, Venkata Sitaramagiridharganesh Ganapavarapu, Ashish Jagmohan, Roman Vaculin
Our central result is a novel protocol that (a) ensures the curator accesses at most $O(K^{\frac{1}{3}}|D_s| + |D_v|)$ points (b) has formal privacy guarantees on the leakage of information between the data owners and (c) closely matches the best known non-private greedy algorithm.