Abdul Fatir Ansari
Machine Learning Scientist at AWS AI Labs
Hi! I am Fatir, an ML Scientist at AWS AI Labs in Berlin, where I work on time series forecasting, log analytics, and generative models. I also contribute to GluonTS.
Research: My general research interest lies in the areas of generative models, encompassing probabilistic generative modeling (both implicit and explicit), variational inference, unsupervised learning, and representation learning. For details about my background and research, please take a look at my curriculum vitae and my google scholar page.
Previously: I graduated with a PhD in Computer Science from NUS School of Computing where I was advised by Dr. Harold Soh. Prior to that, I received my bachelor’s degree in Civil Engineering from IIT Roorkee. During my undergrad years, I also participated in Google Summer of Code in 2016 and 2017.
Contact: abdulfatirs [at] gmail [dot] com
2021, 2022 - Present
2017 - 2022
2013 - 2017
S2016, S2017
news
| Mar 2024 | Our preprint on the Chronos family of pretrained time series forecasting models is now available. |
|---|---|
| Sep 2023 | Our paper on unconditional diffusion models for time series forecasting got accepted at NeurIPS 2023. |
| Jul 2023 | Our preprint on unconditional diffusion models for time series forecasting is now available. |
| Apr 2023 | Our paper on neural continuous-discrete state space models got accepted at ICML 2023 for oral presentation. |
| Jan 2023 | Our preprint on neural continuous-discrete state space models is now available. |
latest posts
| Dec 24, 2020 | Introduction to Gradient Flows in the 2-Wasserstein Space |
|---|---|
| Apr 17, 2020 | Monte Carlo Sampling using Langevin Dynamics |
| Apr 8, 2020 | 1-Wasserstein distance: Kantorovich–Rubinstein duality |