| Abolfazl Hashemi

January 2022: Robust Training in High Dimensions via Block Coordinate Geometric Median Descent accepted to The 2022 International Conference on Artificial Intelligence and Statistics (AISTATS).
December 2021: “On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning,”) accepted to IEEE Transactions on Parallel and Distributed System.
November 2021: “Communication-Efficient Variance-Reduced Decentralized Stochastic Optimization over Time-Varying Directed Graphs”) accepted to IEEE Transactions on Automatic Control.
October 2021: Invited talk at CERIAS on Robustness and Security and in Adversarial Environments (Slides)
September 2021: Invited talks at Purdue CS department and ICON on Collaborative Learning (Slides)
August 2020: Started as an Assistant Professor of ECE at Purdue!
June 2021: New paper out “Robust Generative Adversarial Imitation Learning via Local Lipschitzness”
June 2021: New paper out “Robust Training in High Dimensions via Block Coordinate Geometric Median Descent”
June 2021: New paper out “DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning”
May 2021: “No-Regret Learning with High-Probability in Adversarial Markov Decision Processes” accepted to UAI 2021
March 2021: Our paper “Function Approximation via Sparse Random Features” is trending on DeepAI
March 2021: New paper out “Generalization Bounds for Sparse Random Feature Expansions”
January 2021: Three papers accepted to ICASSP 2021
January 2021: One paper accepted to ACC 2021
January 2021: New paper out “Communication-Efficient Variance-Reduced Decentralized Stochastic Optimization over Time-Varying Directed Graphs”
December 2020: New paper out “Faster Non-Convex Federated Learning via Global and Local Momentum”
November 2020: New paper out “On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization”
September 2020: Started my Postdoc at Oden Institute!
August 2020: I successfully defended my dissertation!