no code implementations • 13 Mar 2024 • Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha, Kaushik Roy
We introduce Verifix, a novel Singular Value Decomposition (SVD) based algorithm that leverages a small, verified dataset to correct the model weights using a single update.
no code implementations • 28 Feb 2024 • Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy
Second, we present a novel insight showing that input loss curvature is upper-bounded by the differential privacy parameter.
no code implementations • 11 Jul 2023 • Isha Garg, Deepak Ravikumar, Kaushik Roy
Second, we inject corrupted samples which are memorized by the network, and show that these are learned with high curvature.
no code implementations • 9 Apr 2023 • Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi, Kaushik Roy
The goal of IDKD is to homogenize the data distribution across the nodes.
no code implementations • 6 May 2022 • Deepak Ravikumar, Kaushik Roy
Therefore, applying a single threshold for all classes is not ideal since the same similarity score represents different uncertainties for different classes.
no code implementations • 29 Sep 2021 • Deepak Ravikumar, Sangamesh Kodge, Isha Garg, Kaushik Roy
This reduces the separability of in-distribution data from OoD data.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 15 Dec 2020 • Deepak Ravikumar, Sangamesh Kodge, Isha Garg, Kaushik Roy
We utilize mixup in two ways to implement Vicinal Risk Minimization.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • 4 Aug 2020 • Deepak Ravikumar, Sangamesh Kodge, Isha Garg, Kaushik Roy
In this work, we study the effect of network architecture, initialization, optimizer, input, weight and activation quantization on transferability of adversarial samples.