Khurshed P. Fitter
I am a Quantum Science and Engineering master's student at EPFL, Switzerland. I am working at Prof. Vincenzo Savona's lab (LTPN) on quantum phase estimation and its applications for efficiently preparing stationary states. I also work on characterizing entanglement in quantum states using measurement statistics. My bachelor's was in Electronics and Communication Engineering at the Visvesvaraya National Institute of Technology, India.
I am also working on Tensor Norms and their applications to Quantum Information at the Laboratoire de Physique Theorique under the supervision of Dr. Ion Nechita, University of Toulouse III, France and Dr. Cécilia Lancien, University of Grenoble, France.
Previously, I worked on Quantum Algorithms for many-body quantum systems with Dr. Juan Carrasquilla and Mohamed Hibat-Allah at the Vector Institute, Canada. I have also worked on cold atom systems and matter-wave lensing with Dr. Wolf von Klitzing at the BEC and Matter Waves group, IELTS-FORTH, Greece.
As a DAAD WISE Scholar, I worked on detecting entanglement in Bose-Einstein Condensates at the Many Body Quantum Dynamics group with Dr. Martin Gärttner at the Kirchhoff Institute for Physics, Heidelberg. I also waddle around with machine learning at IvLabs.
Besides research, I like to spend my time reading and looking at trees and clouds.
News
[Dec 2023] Attended the CECAM-EPFL workshop on Quantum Algorithms for Chemistry and Material Science Simulation.
[Nov 2023] Elected as the President of the Quantum Science and Engineering student association (QET) of EPFL.
[Oct 2023] Attended the Quantum Industry Day in Switzerland organized at EPFL.
[Sept 2023] Started my master's in Quantum Science and Engineering at EPFL, Switzerland.
Publications
Estimating the entanglement of random multipartite quantum states
arXiv: 2209.11754
K. Fitter, C. Lancien, I. Nechita
Our general goal in this work is to numerically estimate the injective norm for randomly sampled tensors. Our results constitute the first numerical estimates on the amount of genuinely multipartite entanglement typically present in various, physically relevant models of random multipartite pure states.
Development of analytical solutions for Photoacoustic Imaging of an extended line source with acoustic lens based reconstruction strategy
International Conference on the Paradigm Shifts in Communication, Embedded Systems, Machine Learning and Signal Processing (PCEMS), 2022
K. Fitter, S. Sinha
Photoacoustic imaging combines the best of both worlds; optical and acoustic imaging. However, most current methods involve huge computational overheads. We present analytical solutions for the imaging of extended line sources using an acoustic lensing setup.
Enhancing Context Through Contrast
NeurIPS 2021 Workshop on Pre-registration in Machine Learning
K. Ambilduke, A. Shetye, D. Bagade, R. Bhagwatkar, K. Fitter, P. Vagdargi, S. Chiddarwar
We posit that languages are linguistic transforms that map abstract meaning to sentences. We attempt to extract and investigate this abstract space by optimizing the Barlow Twins objective between latent representations of parallel sentences.
Paying Attention to Video Generation
NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:139-154, 2021
R. Bhagwatkar, K. Fitter, S. Bachu, A. Kulkarni, S. Chiddarwar
Just like sentences are series of words, videos are series of images. Inspired by the success of large language models in predicting language, we attempt to generate videos using a GPT and a novel Attention-based Discretized Autoencoder.
A Review of Video Generation Approaches
International Conference on Power, Instrumentation, Control and Computing (PICC), 2020
R. Bhagwatkar, K. Fitter, S. Bachu, A. Kulkarni, S. Chiddarwar
In this work we study and discuss several approaches for generating videos, either using Generative Adversarial Networks (GANs) to sequential models like LSTMs. Further, we compare the strengths and weakness of each approach with the underlying motivation to provide a broad and rigorous review on the subject.
Projects
Machine Learning Phases of Matter
Developed machine learning models for detecting phases in toy physical models inspired by previous work.
Implemented feed-forward and convolutional neural networks for detecting topological phases in 2D Ising gauge theories.
Quantum Machine Learning
Developing an open-source repository containing various QML paper implementations.
Variational Quantum Classifier
Explored, designed and cross-validated more than 20 feature maps for binary classification using variational quantum circuits.
Achieved an accuracy of more than 81% on a classified test dataset.
Trained the models for binary classification amongst samples of digits 4 and 9 from the MNIST Dataset, reduced to three dimensions.
Quantum SVM
Implemented a QSVM using Qiskit to develop kernel mappings for fitting hyperplanes corresponding to binary classification tasks.
Performed binary classification on an ad-hoc and breast cancer dataset with more than 99% accuracy.
Medical VQA
Deployed various Visual Question Answering models on medical datasets.
Improved Facebook AI Research’s MMF framework for medical data.
Achieved leaderboard performance on the ImageCLEF-2019 dataset.
Video Generation
Aimed at generating entire frames and not pixel-level predictions.
Developed a novel Attention Based Discretized Autoencocder (ADAE).
Coupled the ADAE with a GPT-2 for video generation.
Neural Machine Translation
Language Modelling
Generated Dinosaur names using Character-level RNNs.
Developed a paragraph generator to generate text from Harry Potter novels.
Implemented RNNs from scratch and compared performance with and amongst different inbuilt RNN modules using PyTorch.
Variational Deep Learning
Studied and implemented various autoencoders and generative networks.
Developing variational models for multimodal applications, mainly sequential multimodal data like electroencephalography signals.
Landmark Retrieval
Aimed at extracting images of landmarks similar to a query image.
Designed a ResNet-101 based autoencoder for the above task on “Google’s Landmark Dataset-v2” using TensorFlow.
Real-time Digit Classifier
Developed an open-source pipeline for human-computer interaction using Deep Learning and Computer Vision for digit classification.
Trained Convolutional and Deep Neural Networks from scratch.
Achieved 99% accuracy on the MNIST Dataset in real-time.
Detection & Tracking
Aimed at object detection and tracking from high altitude aerial vehicles.
Optimized the pipeline to deliver real-time performance with human accuracy.