Researcher
Alokendu Mazumder
Senior Researcher · Fujitsu Research of India

I am a Senior Researcher at the Security Science (SS) Laboratory of Fujitsu Research of India. Previously, I was a Prime Minister's Research Fellow (PMRF) PhD at the Indian Institute of Science, Bengaluru, advised by Prof. Punit Rathore. My doctoral research lies at the intersection of stochastic optimization theory and deep representation learning.

I have had the privilege of conducting research at MIT's Senseable City Lab, Dolby Laboratories (Advanced Technology Group), and IBM Research — working on problems ranging from diffusion bridge models for image restoration to context-length bias in time-series forecasting.

My broader interests span optimization theory, deep learning, computer vision, and stochastic modelling, with a focus on principled, theoretically grounded approaches to modern learning problems.

Optimization Theory Deep Representation Learning Computer Vision
Contact & Links
alokendum@iisc.ac.in +91 70434 54680 Google Scholar alokendumazumder LinkedIn alokendumazumder.github.io
Fujitsu Research of India SS Lab · Senior Researcher, 2026–Present
IISc Bengaluru RBCCPS · PhD Scholar, 2021–2026
MIT Senseable City Lab Visiting Researcher, Summer 2025
IIT Jammu M.Tech CSE, 2019–2021
Alokendu Mazumder
News
July 2026 Paper Global Linear Convergence of Inexact TD under Generalized Smoothness accepted at Transactions on Machine Learning Research.
June 2026 Paper On Hamming-Lipschitz Type Stability of Subdominant (Min-Max) Ultrametric: Theory and Simple Proofs accepted at Transactions on Machine Learning Research.
May 2026 Paper On Convergence of ADAM with Data Dependent Stepsize accepted at IEEE Transactions on Artificial Intelligence (CiteScore 6.4).
Apr 2026 Challenge PosSpec-Net placed 4th at the ICASSP 2026 Radar Acoustic Speech Enhancement Grand Challenge.
Jan 2026 Paper Fractional Gradient Descent with Matrix Stepsizes published in IEEE Transactions on Neural Networks and Learning Systems (Impact Factor 8.9).
Jun 2025 Visit Joined MIT Senseable City Lab as a Visiting Researcher through the MIT-MISTI grant.
Apr 2025 Workshop DIME: Deterministic Information Maximizing Autoencoders accepted at the Workshop on Deep Generative Models @ ICLR 2025.
Jan 2025 Internship Joined Dolby Laboratories (Advanced Technology Group) as a Research Intern, working on diffusion bridge models for image deblurring and dehazing.
May 2024 Internship Joined IBM Research, Bengaluru as an AI Research Intern, working on context-length bias in time-series forecasting models.
Jan 2024 Paper Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoders presented at IEEE/CVF WACV 2024.
Aug 2022 Award Recipient of the Prime Minister's Research Fellowship (PMRF), awarded by the Ministry of Education, Govt. of India.
Publications

* denotes joint co-authorship.  ·  Google Scholar profile →

Journal Articles
TMLR
2026 · Reinforcement Learning
Global Linear Convergence of Inexact TD under Generalized Smoothness
Alokendu Mazumder, Ila Ananta, Punit Rathore
Transactions on Machine Learning Research
Paper
TMLR
2026 · Graph Theory
On Hamming-Lipschitz Type Stability of Subdominant (Min-Max) Ultrametric: Theory and Simple Proofs
Alokendu Mazumder, Arnab Roy, Punit Rathore
Transactions on Machine Learning Research
Paper
IEEE TAI
2026 · Optimisation
On Convergence of ADAM with Data Dependent Stepsize
Alokendu Mazumder, Rishabh Sabharwal, Bhartendu Kumar*, Manan Tayal*, Chirag Garg*, Arnab Roy*, Punit Rathore
IEEE Transactions on Artificial Intelligence
Paper Code
IEEE TNNLS
2025 · Optimisation
Fractional Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
Alokendu Mazumder, Keshav Vyas, Punit Rathore
IEEE Transactions on Neural Networks and Learning Systems
Paper Code
Conference Proceedings
WACV
2024
Learning Low-Rank Latent Spaces Using Simple Deterministic Autoencoders: Theoretical & Empirical Insights
Alokendu Mazumder, Tirthajit Baruah*, Bhartendu Kumar*, Rishab Sharma, Vishwajeet Pattanaik, Punit Rathore
IEEE/CVF Winter Conference on Applications of Computer Vision
Paper Code
ICIP
2021
Perceptual Quality Assessment of DIBR Synthesized Views Using Saliency Based Deep Features
Shubham Chaudhary, Alokendu Mazumder, Deebha Mumtaz, Vinit Jakhetiya, Badri N. Subudhi
IEEE International Conference on Image Processing
Paper
OCEANS
2021
Fusion-UWnet: Multi-channel Fusion-based Deep CNN for Underwater Image Enhancement
Pious Pradhan, Alokendu Mazumder, Srimanta Mandal, Badri N. Subudhi
IEEE OCEANS
Paper
Workshop & Challenge Papers
ICLR (W)
2025
DIME: Deterministic Information Maximizing Autoencoders
Alokendu Mazumder, Chirag Garg, Tirthajit Baruah, Punit Rathore
Workshop on Deep Generative Models @ ICLR 2025
Paper Code
ICASSP
2026
PosSpec-Net: Enhancing Radar-Based Speech Signals via U-Nets and Positional Vectors
Yash Soni, Alokendu Mazumder, Prashant Mishra, Punit Rathore
ICASSP 2026 Radar Acoustic Speech Enhancement Grand Challenge · 4th Place
Results
ICCV (W)
2023
DeepVAT: A Self-Supervised Technique for Cluster Assessment in Image Datasets
Alokendu Mazumder, Tirthajit Baruah, Akash Kumar, Pagadla Krishna Murthy, Vishwajeet Pattanaik, Punit Rathore
IEEE/CVF ICCV Workshops 2023
Paper
Under Review & Work in Progress
Theory
On Convergence of Adagrad Under Generalized Smoothness Draft
Alokendu Mazumder, Ayaan Mohd, Harshit Rawat, Arnab Roy, Mayank Baranwal, Punit Rathore
Deep Learning
LISA: Latent Inference on the Sphere for A-posteriori Sampling Under Review
Alokendu Mazumder, Chirag Garg, Tirthajit Baruah, Punit Rathore
Theoretical RL
Global Linear Convergence of Inexact TD Under Generalized Smoothness Under Review
Alokendu Mazumder, Ila Ananta, Punit Rathore
Teaching

I have served as a Teaching Assistant for the following courses at the Indian Institute of Science, Bengaluru.

Theory and Applications of Bayesian Learning
Jan – Apr
Indian Institute of Science, Bengaluru
Teaching Assistant
Jan – Apr 2022 Jan – Apr 2024 Jan – Apr 2026
Machine Learning for Cyber Physical Systems
Aug – Dec
Indian Institute of Science, Bengaluru
Teaching Assistant
Aug – Dec 2022 Aug – Dec 2023 Aug – Dec 2025
Curriculum Vitae

A full PDF version of my CV is available below.

Download CV (PDF)
Education
2021 – Present
PhD — Stochastic Optimization & Deep Representation Learning
Indian Institute of Science, Bengaluru
Advisor: Dr. Punit Rathore · CGPA: 8.70/10.0 · Expected: July 2026
Funded by the Prime Minister's Research Fellowship (PMRF)
2019 – 2021
M.Tech — Computer Science & Engineering (Data Science)
Indian Institute of Technology Jammu
Thesis: Eigenspace Based Anomaly Detection in Dynamic Graphs · CGPA: 9.02/10.0
Advisor: Dr. Satyadev Ahlawat
Awards & Honours
PMRF
Prime Minister's Research Fellowship
Ministry of Education, Govt. of India · August 2022 cycle · One of India's most prestigious doctoral fellowships.
MIT-MISTI
MIT International Science & Technology Initiative Grant
Joined MIT Senseable City Lab as visiting researcher, Summer 2025.
Technical Skills
Languages

Python · C++

Frameworks & Tools

PyTorch · TensorFlow · OpenCV · Scikit-learn · Pandas · Flask · LaTeX

Domains

Optimization Theory · Deep Learning Theory · Stochastic Modelling · Image Processing · Computer Vision