Md Musfiqur Rahman

I am a Ph.D. student working with Professor Murat Kocaoglu in the School of Electrical and Computer Engineering, at Purdue University.

I apply causal inference to solve trustworthy ML problems using deep generative models and large pre-trained models. Currently, I am exploring areas such as adaptive causal effect estimation, generalization in causal generative models, causal representation learning, and more.

I am a regular reviewer of papers in UAI, ICML, ICLR, AAAI, NeurIPS, AISTAT etc.

You can see my resume here.
Follow me: #Email # Twitter #Github #LinkedIn #Google Scholar

News!

[Summer 2026] Attended the Bloomberg/Columbia Machine Learning Summer School, gaining hands-on experience in RL for LLMs, agents, time-series methods, preference optimization, and mechanistic interpretability; built an autonomous ML research agent etc.
[Summer 2026] Our paper "Decomposing Epistemic Uncertainty for Causal Decision Making" is selected for a SPOTLIGHT presentation at Workshop on Epistemic Intelligence in Machine Learning@ ICML.
[Spring 2026] I am happy to be recognized as a silver reviewer at ICML 2026.
[Summer 2025] I presented a tutorial in UAI 2025 with Professor Murat Kocaoglu on Causal Inference with Deep Learning and Generative Models”. Slides are here.
[Summer 2025] Joined Amazon as a summer intern to contribute to the Pricing and Promotion team. Alhamdulillah! As an Applied Scientist Intern (May-Aug 2025), evaluated a multi-horizon dose-response model using a deep causal architecture on Amazon pricing data, extending it to multiple treatments, and gained experience with time-series ML models evaluated on synthetic and real-world data.
[Spring 2025] Got enlisted as notable reviewer in ICLR.
[Spring 2025] Our paper titled "FeDCM: Federated Learning of Deep Causal Generative Models" is accepted in UAI 2025! .
[Spring 2025] Received my Master of Science degree in Electrical and Computer Engineering from Purdue University
[Spring 2025] Passed my Phd Preliminary examination!
[Fall 2024] Our paper titled "Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand" is accepted in NeurIPS 2024! .
- Presentation: https://recorder-v3.slideslive.com/?share=96768&s=09f41687-e6b3-4daa-ab8e-e751bf277f67
- Paper: https://nips.cc/virtual/2024/poster/93180
[Summer 2024] Our paper titled “Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference” is accepted at ICML’24.
- Presentation: https://youtu.be/TvWHdvfHk2o
- Paper: https://icml.cc/virtual/2024/poster/33643
[Summer 2024] Joined Genentech as a summer intern to contribute in Causal ML projects.
[Spring 2023] Our paper 'Towards Modular Learning of Deep Causal Generative Models' has been accepted for poster presentation at SCIS 2023 and SPIGM 2023 workshops.
[Spring 2023] I have been identified as one of the Top Reviewers at UAI 2023.
[Spring 2023] Our paper "Finding Invariant Predictors Efficiently via Causal Structure" has been accepted at UAI 2023.

RESEARCH EXPERIENCE

Uncertainty-aware Causal Decision Making via Effect Bound Decomposition
- Workshop on Epistemic Intelligence in Machine Learning, ICML [Spotlight, EIML@ICML 2026] (Under review, NeurIPS 2025)
- Developed a novel decomposition of causal effect bounds into structural and sample uncertainty, providing a principled criterion for when more data cannot improve optimal action selection under non identifiability.
- Collaborated with Intuit AI Research on a middle ground approach bridging causal modeling and traditional ML.
FeDCM: Federated Learning of Deep Causal Generative Models
- 41st Conference on Uncertainty in Artificial Intelligence [UAI 2025]
- Explored federated learning of causal generative models across domains without sharing raw data.
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
- 38th Conference on Neural Information Processing Systems [NeurIPS 2024].
- Proposed a diffusion-based approach to sample from interventional distributions given arbitrary causal graphs with latent confounders; demonstrated on the MIMIC-Chest X-ray dataset.
Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference
- 41st International Conference on Machine Learning, PMLR 235:41886-41926 [ICML 2024]
- Developed a deep causal generative model to learn high-dimensional data distributions in a modular fashion, enabling the use of pre-trained models for causal and counterfactual effect estimation.
- Built expertise in classifier-free diffusion models, conditional GANs, and auto-encoders.
Towards Modular Learning of Deep Causal Generative Models
- Workshop on Structured Probabilistic Inference & Generative Modeling; Workshop on Spurious Correlations, Invariance, and Stability [ICML 2023 Workshops]. See workshop paper.
Finding Invariant Predictors Efficiently via Causal Structure
- Uncertainty in Artificial Intelligence, PMLR [UAI 2023]
- Provided a graphical characterization of the identifiability of conditional causal queries and leverage it with greedy search to develop a sound algorithm called ID4IP for finding invariant estimators in polynomial time given the causal graph structure.
Accelerating Recursive Partition-based Causal Structure Learning
- 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2021). (See Full Paper)
- Accelerated recursive partition-based causal structure learning and reduced the number of Conditional independence tests for detecting false edges up to 86%.
Speeding up Distributed Pseudo-tree Optimization Procedures with Cross Edge Consistency to Solve DCOPs
- Applied Intelligence, 51(3):1733-1746, 2021
- Accomplished higher parallelism and reduced message size to solve Distributed Constraint Optimization Problem in 4% - 96% faster runtime.

Google Sites

Report abuse

Page details

Page updated

Google Sites

Report abuse