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.
1 code implementation • 1 Dec 2023 • Sangamesh Kodge, Gobinda Saha, Kaushik Roy
We demonstrate our algorithm's efficacy on ImageNet using a Vision Transformer with only $\sim$1. 5% drop in retain accuracy compared to the original model while maintaining under 1% accuracy on the unlearned class samples.
1 code implementation • 28 Sep 2022 • Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Our experiments demonstrate that \textit{NGC} and \textit{CompNGC} outperform (by $0-6\%$) the existing SoTA decentralized learning algorithm over non-IID data with significantly less compute and memory requirements.
1 code implementation • 17 Nov 2021 • Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
In this paper, we propose and show the convergence of low precision decentralized training that aims to reduce the computational complexity and communication cost of decentralized training.
no code implementations • 18 Oct 2021 • Sangamesh Kodge, Kaushik Roy
Experiments on the probing task from SentEval dataset show that our model performs up to $4. 65\%$ better in accuracy than the baseline with an average improvement of $2. 67\%$ on the semantic tasks.
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.
no code implementations • 27 Mar 2020 • Mustafa Ali, Akhilesh Jaiswal, Sangamesh Kodge, Amogh Agrawal, Indranil Chakraborty, Kaushik Roy
`In-memory computing' is being widely explored as a novel computing paradigm to mitigate the well known memory bottleneck.