I am a Ph.D. candidate in the Electical and Computer Engineering Department at College of Engineering, Boston University. I am part of Prof. Venkatesh Saligrama’s lab. I’m currently working on constrained learning, and efficient deep neural architectures. Previously, I was a research fellow in the Machine Learning & Optimization Group at Microsoft Research, India, where I worked with Dr. Manik Varma on Extreme Classification. I was an undergraduate student at IIT Guwahati where I obtained my B. Tech. in Computer Science in 2014. I worked on Live Streaming via Peer to Peer Overlay Networks with Prof. Diganta Goswami for my undergraduate thesis. I’ve also worked as a Software Engineer for two years at Dynamics CRM, Microsoft India Development Center, Bangalore.
Announcement. I am looking for a full-time research position in the industry. Contact me if you think I will be a good fit for your team. I have attached my curriculum vitae, cover letter, and research statement.
anilkagak2 @ gmail
Boston, Massachusetts, USA
news
| Jan 21, 2023 | Scaffolding a Student to Instill Knowledge and Efficient Edge Inference by Selective Query have been accepted at ICLR 2023. |
|---|---|
| Jun 16, 2022 | Achieving High TinyML Accuracy through Selective Cloud Interactions has been accepted at DyNN Workshop at ICML 2022. |
| Mar 4, 2022 | Condensing CNNs with Partial Differential Equations has been accepted at CVPR 2022. |
| May 8, 2021 | Training Recurrent Neural Networks via Forward Propagation Through Time has been accepted at ICML 2021. |
| Mar 4, 2021 | Time Adaptive RNN: A Dynamical Systems View has been accepted at CVPR 2021. |
| Jan 28, 2021 | Selective Classification via One-Sided Prediction has been accepted at AISTATS 2021. |
| Jun 1, 2020 | Selected as a Hariri Graduate Student Fellow, Rafik Hariri Institute for Computing and Computational Scince & Engineering, Boston University. |
| Dec 19, 2019 | RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? has been accepted at ICLR 2020. |