Abhimanyu Das
Email: {first four characters of my first name followed by dot followed by my last name}@gmail.com
I am a Research Scientist at Google. My research interests span topics in machine learning, data-mining and theoretical computer science. Prior to Google, I was a Researcher at Microsoft Research and at Yahoo! Labs.
I obtained a PhD in Computer Science from the University of Southern California under the supervision of David Kempe, and a B. Tech in Computer Science from IIT Delhi. My PhD research focused on algorithms for subset selection and sparse approximation. Prior to my PhD, I also spent several years in the industry (Cortina Systems and Mahi Networks), where I worked on software stacks for networking and embedded systems.
My work has received a Distinguished Paper Award at the International Conference on Machine Learning (ICML) 2011, a Best Paper Award at the ACM Conference on Web Search and Data Mining (WSDM) 2014, and a Best Paper Honorable Mention Award at the Web Conference (WWW) 2018.
Selected Publications (full list):
Abhimanyu Das, Weihao Kong, Rajat Sen, Yichen Zhou: "A decoder-only foundation model for time-series forecasting", ICML 2024
Reese Pathak, Rajat Sen, Weihao Kong, Abhimanyu Das: "Transformers can optimally learn regression mixture models", ICLR 2024
Abhimanyu Das, Weihao Kong, Andrew Leach, Shaan Mathur, Rajat Sen, Rose Yu: "Long-term Forecasting with TiDE: Time-series Dense Encoder", TMLR August 2023
Ayush Jain, Weihao Kong, Rajat Sen, Abhimanyu Das: "Efficient List-Decodable Regression using Batches", ICML 2023
Abhimanyu Das, Weihao Kong, Biswajit Paria, Rajat Sen: "Dirichlet Proportions Model for Hierarchically Coherent Probabilistic Forecasting", UAI 2023
Ashok Cutkosky, Abhimanyu Das, Weihao Kong, Chansoo Lee, Rajat Sen: "Blackbox optimization of unimodal functions", UAI 2023
Pranjal Awasthi, Abhimanyu Das, Weihao Kong, Rajat Sen: "Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models", NeurIPS 2022
Pranjal Awasthi, Abhimanyu Das, Rajat Sen, Ananda Theertha Suresh: "On the Benefits of Maximum Likelihood Estimation for Regression and Forecasting", ICLR 2022
Ashok Cutkosky, Chris Dann, Abhimanyu Das, Richard Zhang: "Leveraging Initial Hints for Free in Stochastic Linear Bandits", ALT 2022
Pranjal Awasthi, Abhimanyu Das, Sreenivas Gollapudi: "Beyond GNNs: An Efficient Architecture for Graph Problems", AAAI 2022
Pranjal Awasthi, Abhimanyu Das, Sreenivas Gollapudi: "A Convergence Analysis of Gradient Descent on Graph Neural Networks", NeurIPS 2021
Ayya Alieva, Ashok Cutkosky, Abhimanyu Das: "Robust Pure Exploration in Linear Bandits with Limited Budget", ICML 2021
Ashok Cutkosky, Chris Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit: "Dynamic Balancing for Model Selection in Bandits and Reinforcement Learning", ICML 2021
Atish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang, Richard Zhang: "One network fits all? Modular versus monolithic task formulations in neural networks", ICLR 2021
Abhimanyu Das, Sreenivas Gollapudi, Ravi Kumar, Rina Panigrahy: "On the Learnability of Random Deep Networks", ACM SODA 2020
Abhimanyu Das, Sreenivas Gollapudi, Anthony Kim, Debmalya Panigrahi, Chaitanya Swamy: "Minimizing Latency in Online Ride and Delivery Services", WWW 2018 (best paper honorable mention)
Flavio Chierichetti, Abhimanyu Das, Anirban Dasgupta, Ravi Kumar: “Approximate Modularity”, IEEE FOCS 2015
Abhimanyu Das, Sreenivas Gollapudi, Kamesh Munagala, “Modeling Opinion Dynamics in Social Networks”, WSDM 2014.
Amr Ahmed, Abhimanyu Das, Alexander Smola, “Hierarchical multitask learning: scalable algorithms and applications in display advertising”, WSDM 2014 (best paper award).
Abhimanyu Das, Sreenivas Gollapudi, Rina Panigrahy, Mahyar Salek, “Debiasing Social Wisdom”, KDD 2013.
Neha Gupta, Abhimanyu Das, Sandeep Pandey, Vijay Narayanan, “Factoring Past Exposure in Display Advertising Targeting”, KDD 2012.
Abhimanyu Das, Anirban Dasgupta, Ravi Kumar, “Selecting Diverse Features using Spectral Regularization”, NIPS 2012
Abhimanyu Das, David Kempe: "Submodular meets Spectral – Greedy Algorithms for Subset Selection and Sparse Approximation ", ICML 2011 (distinguished paper award)
Abhimanyu Das, David Kempe: "Algorithms for Subset Selection in Linear Regression, ACM Symposium on Theory of Computing, STOC 2008