Search Results for author: Pawan Kumar

Found 27 papers, 6 papers with code

A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks

1 code implementation10 Apr 2024 Neel Mishra, Bamdev Mishra, Pratik Jawanpuria, Pawan Kumar

It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse.

Image Generation Second-order methods

Enhancing ML model accuracy for Digital VLSI circuits using diffusion models: A study on synthetic data generation

no code implementations15 Oct 2023 Prasha Srivastava, Pawan Kumar, Zia Abbas

Generative AI has seen remarkable growth over the past few years, with diffusion models being state-of-the-art for image generation.

Data Augmentation Image Generation +1

Alpha Elimination: Using Deep Reinforcement Learning to Reduce Fill-In during Sparse Matrix Decomposition

no code implementations15 Oct 2023 Arpan Dasgupta, Pawan Kumar

A common problem faced during this decomposition is that even though the given matrix may be very sparse, the decomposition may lead to a denser triangular factors due to fill-in.

Decision Making

Reinforcement Learning Based Sensor Optimization for Bio-markers

no code implementations21 Aug 2023 Sajal Khandelwal, Pawan Kumar, Syed Azeemuddin

Radio frequency (RF) biosensors, in particular those based on inter-digitated capacitors (IDCs), are pivotal in areas like biomedical diagnosis, remote sensing, and wireless communication.


Explainable machine learning to enable high-throughput electrical conductivity optimization and discovery of doped conjugated polymers

no code implementations8 Aug 2023 Ji Wei Yoon, Adithya Kumar, Pawan Kumar, Kedar Hippalgaonkar, J Senthilnath, Vijila Chellappan

For the subset of highly conductive samples, we employed a regression model to predict their conductivities, yielding an impressive test R2 value of 0. 984.

Nonnegative Low-Rank Tensor Completion via Dual Formulation with Applications to Image and Video Completion

no code implementations13 May 2023 Tanmay Kumar Sinha, Jayadev Naram, Pawan Kumar

Recent approaches to the tensor completion problem have often overlooked the nonnegative structure of the data.

Image Inpainting

Structured Low-Rank Tensor Learning

no code implementations13 May 2023 Jayadev Naram, Tanmay Kumar Sinha, Pawan Kumar

We consider the problem of learning low-rank tensors from partial observations with structural constraints, and propose a novel factorization of such tensors, which leads to a simpler optimization problem.

Riemannian optimization

Angle based dynamic learning rate for gradient descent

1 code implementation20 Apr 2023 Neel Mishra, Pawan Kumar

In our work, we propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks.

Image Classification

Adaptive Consensus Optimization Method for GANs

no code implementations20 Apr 2023 Sachin Kumar Danisetty, Santhosh Reddy Mylaram, Pawan Kumar

The proposed method is fastest to obtain similar accuracy when compared to prominent second order methods.

Image Generation Second-order methods

Light-weight Deep Extreme Multilabel Classification

1 code implementation20 Apr 2023 Istasis Mishra, Arpan Dasgupta, Pratik Jawanpuria, Bamdev Mishra, Pawan Kumar

Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels.

Classification Multi-Label Learning

marl-jax: Multi-Agent Reinforcement Leaning Framework

1 code implementation24 Mar 2023 Kinal Mehta, Anuj Mahajan, Pawan Kumar

We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents.

Multi-agent Reinforcement Learning reinforcement-learning +1

Qualitative Data Augmentation for Performance Prediction in VLSI circuits

no code implementations15 Feb 2023 Prasha Srivastava, Pawan Kumar, Zia Abbas

Various studies have shown the advantages of using Machine Learning (ML) techniques for analog and digital IC design automation and optimization.

Data Augmentation

SynGraphy: Succinct Summarisation of Large Networks via Small Synthetic Representative Graphs

no code implementations15 Feb 2023 Jérôme Kunegis, Pawan Kumar, Jun Sun, Anna Samoilenko, Giuseppe Pirró

In this paper we take the problem of visualising large graphs from a novel perspective: we leave the original graph's nodes and edges behind, and instead summarise its properties such as the clustering coefficient and bipartivity by generating a completely new graph whose structural properties match that of the original graph.

Graph Mining Graph Sampling

Review of Extreme Multilabel Classification

no code implementations12 Feb 2023 Arpan Dasgupta, Siddhant Katyan, Shrutimoy Das, Pawan Kumar

Compared to traditional multilabel classification, here the number of labels is extremely large, hence, the name extreme multilabel classification.


SCIMAT: Science and Mathematics Dataset

1 code implementation30 Sep 2021 Neeraj Kollepara, Snehith Kumar Chatakonda, Pawan Kumar

In this work, we announce a comprehensive well curated and opensource dataset with millions of samples for pre-college and college level problems in mathematicsand science.

On Riemannian Approach for Constrained Optimization Model in Extreme Classification Problems

no code implementations30 Sep 2021 Jayadev Naram, Tanmay Kumar Sinha, Pawan Kumar

We propose a novel Riemannian method for solving the Extreme multi-label classification problem that exploits the geometric structure of the sparse low-dimensional local embedding models.

Extreme Multi-Label Classification Riemannian optimization

Multiphase modelling of glioma pseudopalisading under acidosis

no code implementations29 Jun 2021 Pawan Kumar, Christina Surulescu, Anna Zhigun

We propose a multiphase modeling approach to describe glioma pseudopalisade patterning under the influence of acidosis.

Direct Opto-Electronic Imaging of 2D Semiconductor - 3D Metal Buried Interfaces

no code implementations28 Jan 2021 Kiyoung Jo, Pawan Kumar, Joseph Orr, Surendra B. Anantharaman, Jinshui Miao, Michael Motala, Arkamita Bandyopadhyay, Kim Kisslinger, Christopher Muratore, Vivek B. Shenoy, Eric Stach, Nicholas Glavin, Deep Jariwala

To be specific, potential, conductance and photoluminescence at the buried metal/MoS2 interface are correlated as a function of a variety of metal deposition conditions as well as the type of metal contacts.

Mesoscale and Nanoscale Physics Materials Science Applied Physics Optics

The polar precursor method for solar cycle prediction: comparison of predictors and their temporal range

no code implementations13 Jan 2021 Pawan Kumar, Melinda Nagy, Alexandre Lemerle, Bidya Binay Karak, Kristof Petrovay

The polar precursor method is widely considered to be the most robust physically motivated method to predict the amplitude of an upcoming solar cycle. It uses indicators of the magnetic field concentrated near the poles around sunspot minimum.

Solar and Stellar Astrophysics Space Physics

A Survey on Semantic Parsing from the perspective of Compositionality

no code implementations29 Sep 2020 Pawan Kumar, Srikanta Bedathur

In section 3 we will consider systems that uses formal languages e. g. $\lambda$-calculus (Steedman, 1996), $\lambda$-DCS (Liang, 2013).

Knowledge Base Question Answering Semantic Composition +1

A flux-limited model for glioma patterning with hypoxia-induced angiogenesis

no code implementations21 Sep 2020 Pawan Kumar, Christina Surulescu

We propose a model for glioma patterns in a microlocal tumor environment under the influence of acidity, angiogenesis, and tissue anisotropy.

Multiscale modeling of glioma pseudopalisades: contributions from the tumor microenvironment

no code implementations10 Jul 2020 Pawan Kumar, Jing Li, Christina Surulescu

Moreover, we study two different types of scaling and compare the behavior of the obtained macroscopic PDEs by way of simulations.

Optimizing Non-decomposable Measures with Deep Networks

no code implementations31 Jan 2018 Amartya Sanyal, Pawan Kumar, Purushottam Kar, Sanjay Chawla, Fabrizio Sebastiani

We present a class of algorithms capable of directly training deep neural networks with respect to large families of task-specific performance measures such as the F-measure and the Kullback-Leibler divergence that are structured and non-decomposable.

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