Search Results for author: Bhartendu Kumar

Found 3 papers, 2 papers with code

Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights

1 code implementation24 Oct 2023 Alokendu Mazumder, Tirthajit Baruah, Bhartendu Kumar, Rishab Sharma, Vishwajeet Pattanaik, Punit Rathore

In LoRAE, we incorporated a low-rank regularizer to adaptively reconstruct a low-dimensional latent space while preserving the basic objective of an autoencoder.

Image Generation

On the Contractivity of Plug-and-Play Operators

1 code implementation28 Sep 2023 Chirayu D. Athalye, Kunal N. Chaudhury, Bhartendu Kumar

The present work is motivated by the following questions: Can we relax the assumptions on the forward model?

Image Inpainting

A Theoretical and Empirical Study on the Convergence of Adam with an "Exact" Constant Step Size in Non-Convex Settings

no code implementations15 Sep 2023 Alokendu Mazumder, Rishabh Sabharwal, Manan Tayal, Bhartendu Kumar, Punit Rathore

Lastly, (iii) we also demonstrate that our derived constant step size has better abilities in reducing the gradient norms, and empirically, we show that despite the accumulation of a few past gradients, the key driver for convergence in Adam is the non-increasing step sizes.

Cannot find the paper you are looking for? You can Submit a new open access paper.