**New paper!**

- "Stochastic ISTA/FISTA Adaptive Step Search Algorithms for Convex Composite Optimization" - joint work with Trang H. Tran (Cornell) and Katya Scheinberg (Cornell).

**Our book "**

*Federated Learning: Theory and Practice*" - co-edited with Trong Nghia Hoang (WSU) and Pin-Yu Chen (IBM) has been published by the Elsevier publisher. Thank all the contributors to the book!**2023-12-15:**

### 2023

**One paper was accepted to SDM 2024**.

- "Multi-polytope Machine for Classification" - joint work with Dzung Phan (IBM), Jayant Kalagnanam (IBM), and Chandra Reddy (IBM).

**I will serve as an Area Chair for UAI 2024**.

**Our nomination "**

*Research Contributions to Time Series Foundation Models*" has been selected for 2023 IBM Research Accomplishments.**Two papers were accepted to AAAI 2024**.

- "On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods" - joint work with Anh Duc Nguyen (National University of Singapore), Tuan Dung Nguyen (Autralian National University), Quang Nguyen (MIT), Hoang Nguyen (Georgia Tech), and Kim-Chuan Toh (National University of Singapore).

- "One Step Closer to Unbiased Aleatoric Uncertainty Estimation" - joint work with Wang Zhang (MIT), Martin Ma (Harvard), Subhro Das (MIT-IBM), Tsui-Wei Weng (UCSD), Alexandre Megretski (MIT), and Luca Daniel (MIT).

**I will serve as an Area Chair for ICML 2024. I am also the Champion for ICML conference at IBM Research**.

**Our paper has been accepted for publication to Journal of Machine Learning Research (JMLR)**.

- "On Unbalanced Optimal Transport: Gradient Methods, Sparsity and Approximation Error" - joint work with Quang M. Nguyen (MIT), Hoang H. Nguyen (Georgia Tech), and Yi Zhou (IBM).

**New paper!**

- "A Supervised Contrastive Learning Pretrain-Finetune Approach for Time Series" - joint work with Trang H. Tran (Cornell), Kyongmin Yeo (IBM), Nam Nguyen (IBM), and Roman Vaculin (IBM).

**New paper!**

- "Correlated Attention in Transformers for Multivariate Time Series" - joint work with Quang M. Nguyen (MIT) and Subhro Das (IBM).

**Our patent "A Method for Tuning Hyperparameters for Classification" has been granted**.

**Two papers were accepted to NeurIPS 2023**.

- "On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms" - joint work with Trang H. Tran (Cornell).

- "Analyzing Generalization of Neural Networks through Loss Path Kernels" - joint work with Yilan Chen (UCSD), Wei Huang (RIKEN), Hao Wang (IBM), Charlotte Loh (MIT), Akash Srivastava (IBM), and Tsui-Wei Weng (UCSD).

**Two papers were accepted to IEEE ICDM 2023**.

- "Promoting Robustness of Randomized Smoothing: Two Cost-Effective Approaches" - joint work with Linbo Liu (Amazon), Trong Nghia Hoang (Washington State University), and Tsui-Wei Weng (UCSD).

- "Attacking c-MARL More Effectively: A Data Driven Approach" - joint work with Nhan Pham (IBM), Jie Chen (IBM), Hoang Thanh Lam (IBM), Subhro Das (IBM), and Tsui-Wei Weng (UCSD).

**I will serve as an Area Chair for AISTATS 2024**.

**I will serve as an Area Chair for ICLR 2024**.

**Our paper "A Hybrid Stochastic Optimization Framework for Composite Nonconvex Optimization" has been selected as a winner of the 2022 Pat Goldberg Memorial Best Paper competition**.

**New paper!**

- "Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent" - joint work with Toan N. Nguyen (Uconn), Phuong Ha Nguyen (eBay), and Marten van Dijk (CWI).

**I will serve as an Area Chair for CVPR 2024**.

**Our patent "Optimal Interpretable Decision Trees Using Integer Linear Programming Techniques" has been granted**.

**New paper!**

- "Learning Robust and Consistent Time Series Representations: A Dilated Inception-Based Approach" - joint work with Anh Duy Nguyen (VinUni, UIUC), Trang H. Tran (Cornell), Hieu H. Pham (VinUni, UIUC), and Phi Le Nguyen (HUST).

**New paper!**

- "An End-to-End Time Series Model for Simultaneous Imputation and Forecast" - joint work with Trang H. Tran (Cornell), Kyongmin Yeo (IBM Research), Nam Nguyen (IBM Research), Dzung Phan (IBM Research), Roman Vaculin (IBM Research), and Jayant Kalagnanam (IBM Research).

**I receive 4 IBM Outstanding Technical Achievement Awards for my contributions to the "Dynamic Approaches for Machine Learning", "Regression Optimization for Heavy Processing Industries", "Combinatorial Sparsity for AI", and "Federated Learning Security and Privacy" accomplishments**.

**Our patent "Site-wide Operations Management Optimization for Manufacturing and Processing Control" has been granted**.

**One paper was accepted to ICML 2023**.

- "ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction" - joint work with Wang Zhang (MIT), Tsui-Wei Weng (UCSD), Subhro Das (MIT-IBM), Alexandre Megretski (MIT), and Luca Daniel (MIT).

**I will serve as an Area Chair for NeurIPS 2023**.

**I will serve as a Journal Chair in the Organizing Committee for NeurIPS 2023**.

**One paper was accepted to ICASSP 2023**.

- "Scalable and Secure Federated XGBoost" - joint work with Quang Nguyen (MIT) and Nhan Khanh Le (TUM).

**We organize our AAAI 2023 workshop "When Machine Learning meets Dynamical Systems: Theory and Applications"**. Our invited speakers are Prof. J. Nathan Kutz (University of Washington), Prof. Chuchu Fan (MIT), and Prof. Elad Hazan (Princeton University)

**New paper!**

- "ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction" - joint work with Wang Zhang (MIT), Tsui-Wei Weng (UCSD), Subhro Das (MIT-IBM), Alexandre Megretski (MIT), and Luca Daniel (MIT).

**Our patent "Shuffling-Type Gradient Method for Training Machine Learning models with Big Data" has been granted**.

**One paper was accepted to ICLR 2023**.

- "Label-free Concept Bottleneck Models" - joint work with Tuomas Oikarinen (UCSD), Subhro Das (MIT-IBM), and Lily Weng (UCSD).

**Our paper was accepted to The 2023 American Control Conference (ACC 2023)**.

- "Optimal Control via Linearizable Deep Learning" - joint work with Vinicius Lima (Upenn), Dzung T. Phan (IBM Research), and Jayant R. Kalagnanam (IBM Research).

**2022-12-20:**

### 2022

**I will serve as an Area Chair for ICML 2023. I am also the Champion for ICML conference at IBM Research**.

**Four IBM Research Accomplishments 2022:**

- "

- "

- "

- "

Thank for the great efforts and contributions of my colleagues and collaborators!!!

- "

*Dynamic Approaches for Machine Learning*" (A-level).- "

*Regression Optimization for Heavy Processing Industries*" (A-level).- "

*Combinatorial Sparsity for AI*" (A-level).- "

*Federated Learning Security and Privacy*" (O-level).Thank for the great efforts and contributions of my colleagues and collaborators!!!

**New paper!**

- "Generalizing DP-SGD with Shuffling and Batching Clipping" - joint work with Marten van Dijk (CWI), Phuong Ha Nguyen (eBay), and Toan N. Nguyen (Uconn).

**It is my pleasure to be selected as an IBM Master Inventor. Thanks for all the help from my colleagues, students, and collaborators!!!.**

**I will organize the session "Optimization for Machine Learning" at INFORMS Annual Meeting 2022 on Monday October 17.**

**I will serve as an Area Chair for CVPR 2023**.

**Our workshop proposal was accepted to AAAI 2023**.

Workshop

**"When Machine Learning meets Dynamical Systems: Theory and Applications"**- Co-organizers: Trang H. Tran (Cornell), Wang Zhang (MIT), Subhro Das (MIT-IBM Lab), and Tsui-Wei (Lily) Weng (UCSD).

**MIT-IBM proposal**"

*Safe Learning for Time Series Problems: Data, Structure and Optimization*" (with Luca Daniel (MIT), Alexandre Megretski (MIT), and Subhro Das (MIT-IBM Lab)) has been accepted for a multiple-year award.

**I will serve as an Area Chair for ICLR 2023 for the third consecutive year**.

**I will serve as an Area Chair for AISTATS 2023 for the third consecutive year**.

**I will be a Session Chair of two sessions Optimization/Reinforcement Learning and OPT: Non-Convex at ICML 2022.**

**New paper!**

- "Finding Optimal Policy for Queueing Models: New Parameterization" - joint work with Trang H. Tran (Cornell) and Katya Scheinberg (Cornell).

**New paper!**

- "On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms" - joint work with Trang H. Tran (Cornell).

**I serve as an Action Editor for Journal of Machine Learning Research (JMLR).**

**I serve as an Associate Editor for Journal of Optimization Theory and Applications (JOTA).**

**I receive IBM Outstanding Technical Achievement Award for my contributions to the "Stochastic Gradient Methods: Theory and Applications" accomplishment**.

**One paper was accepted to ICML 2022**.

- "Nesterov Accelerated Shuffling Gradient Method for Convex Optimization" - joint work with Trang H. Tran (Cornell) and Katya Scheinberg (Cornell).

**Our paper has been accepted for publication to Computational Optimization and Applications (COAP)**.

- "Finite-Sum Smooth Optimization with SARAH" - joint work with Marten van Dijk (CWI), Dzung T. Phan (IBM Research), Phuong Ha Nguyen (eBay), Tsui-Wei (Lily) Weng (UCSD), and Jayant R. Kalagnanam (IBM Research).

**I will serve as an Area Chair for NeurIPS 2022.**

**Our paper has been accepted for publication to INFORMS Journal on Applied Analytics (IJAA)**.

- "AI-based Real-time Site-wide Optimization for Process Manufacturing" - joint work with IBM colleagues Jayant Kalagnanam, Dzung Phan, Pavankumar Murali, Dharmashankar Subramanian, Raju Pavuluri, Xiang Ma, and Crystal Lui.

**New papers!**

- "Nesterov Accelerated Shuffling Gradient Method for Convex Optimization" - joint work with Trang H. Tran (Cornell) and Katya Scheinberg (Cornell).

- "Finite-Sum Optimization: A New Perspective for Convergence to a Global Solution" - joint work with Trang H. Tran (Cornell) and Marten van Dijk (CWI).

- "On the Convergence of Gradient Extrapolation Methods for Unbalanced Optimal Transport" - joint work with Quang Minh Nguyen (MIT), Hoang H. Nguyen (Geogia Tech), and Yi Zhou (IBM Research).

- "Evaluating Robustness of Cooperative MARL: A Model-based Approach" - joint work with Nhan H. Pham (IBM Research), Jie Chen (MIT-IBM Lab), Hoang Thanh Lam (IBM Research), Subhro Das (MIT-IBM Lab), and Tsui-Wei Weng (UCSD).

**I have been selected to serve as a Panelist for National Science Foundation (NSF) this year**.

**2021-12-19:**

### 2021

**One paper was accepted to SDM22**.

- "StepDIRECT - A Derivative-Free Optimization Method for Stepwise Functions" - joint work with Dzung Phan (IBM Research) and Hongsheng Liu (UNC).

**Our paper has been accepted for publication to IEEE Access**.

- "Besting the Black-Box: Barrier Zones for Adversarial Example Defense" - joint work with Kaleel Mahmood (Uconn) Phuong Ha Nguyen (eBay), Thanh Nguyen (Amazon), and Marten van Dijk (CWI).

**We are organizing our workshop "New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership" (NFFL 2021) at NeurIPS 2021**.

**Our nomination "**

*Stochastic Gradient Methods: Theory and Applications*" has been selected for 2021 IBM Research Accomplishments. Thanks for the great efforts and contributions of the team with Lam M. Nguyen, Dzung Phan, Pin-Yu Chen, Tsui-Wei Weng, Jayant Kalagnanam**I will serve as an Area Chair for ICML 2022 for the third consecutive year**.

**One paper was accepted to AAAI-22**.

- "Interpretable Clustering via Multi-Polytope Machines" - joint work with Connor Lawless (Cornell University), Jayant Kalagnanam (IBM Research), Dzung Phan (IBM Research), and Chandra Reddy (IBM Research).

**I will serve as an Area Chair for UAI 2022.**

**I organize the session "Recent Advances in Stochastic Gradient Algorithms" at INFORMS Annual Meeting 2021.**

**I will serve as an Associate Editor for IEEE Transactions on Neural Networks and Learning Systems journal.**

**Three papers were accepted to NeurIPS 2021**.

- "FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill), Nhan H. Pham (UNC Chapel Hill), and Dzung T. Phan (IBM Research).

- "Ensembling Graph Predictions for AMR Parsing" - joint work with Thanh Lam Hoang (IBM Research), Gabriele Picco (IBM Research), Yufang Hou (IBM Research), Young-Suk Lee (IBM Research), Dzung T. Phan (IBM Research), Vanessa López (IBM Research), and Ramon Fernandez Astudillo (IBM Research).

- "On the Equivalence between Neural Network and Support Vector Machine" - joint work with Yilan Chen (University of California San Diego), Wei Huang (University of Technology Sydney), and Tsui-Wei Weng (University of California San Diego).

**I will serve as an Action Editor for Neural Networks journal starting 2022.**

**Our paper has been accepted for publication to Journal of Machine Learning Research (JMLR)**.

- "A Unified Convergence Analysis for Shuffling-Type Gradient Methods" - joint work with Quoc Tran-Dinh (UNC), Dzung T. Phan (IBM Research), Phuong Ha Nguyen (eBay), and Marten van Dijk (CWI).

**Our patent has been granted**.

- "Prediction Optimization for System-level Production Control" - joint work with Dzung T. Phan (IBM Research), Pavankumar Murali (IBM Research), and Jayant R. Kalagnanam (IBM Research).

**Our workshop proposal was accepted to NeurIPS 2021**.

Workshop

**"New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership"**- Co-organizers: Nghia Hoang (Amazon AWS AI Labs), Pin-Yu Chen (IBM Research), Tsui-Wei (Lily) Weng (MIT-IBM Watson AI Lab, University of California San Diego), Sara Magliacane (University of Amsterdam), Bryan Kian Hsiang Low (National University of Singapore), and Anoop Deoras (Amazon AWS AI Labs).

**I will serve as a Senior Program Committee (Meta-Reviewer) for AAAI-22.**

**I will be a Session Chair of two sessions Optimization (Stochastic) and Optimization (Nonconvex) at ICML 2021.**

**I will serve as an Area Chair for AISTATS 2022.**

**I will serve as an Action Editor for Machine Learning journal.**

**I will serve as an Area Chair for ICLR 2022**.

**One paper was accepted to ICML 2021**.

- "SMG: A Shuffling Gradient-Based Method with Momentum" - joint work with Trang H. Tran (Cornell) and Quoc Tran-Dinh (UNC Chapel Hill).

**I will serve as a Session Chair of "Oral Session 6" at ICLR 2021**.

**I will serve as a Session Chair of the session "Theory and Practice of Machine Learning" at AISTATS 2021**.

**New paper!**

- "Federated Learning with Randomized Douglas-Rachford Splitting Methods" - joint work with Nhan H. Pham (UNC Chapel Hill), Dzung T. Phan (IBM Research), and Quoc Tran-Dinh (UNC Chapel Hill).

**New paper!**

- "Differential Private Hogwild! over Distributed Local Data Sets" - joint work with Marten van Dijk (Uconn & CWI), Nhuong V. Nguyen (Uconn), Toan N. Nguyen (Uconn), and Phuong Ha Nguyen (eBay).

**Our paper was accepted to The 2021 American Control Conference (ACC 2021)**.

- "

__Regression Optimization for System-level Production Control__" - joint work with Dzung T. Phan (IBM Research), Pavankumar Murali (IBM Research), Nhan H. Pham (UNC), Hongsheng Liu (UNC), and Jayant R. Kalagnanam (IBM Research).

**One paper was accepted to AISTATS 2021**.

- "Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes" - joint work with Nhuong V. Nguyen (Uconn), Toan N. Nguyen (Uconn), Phuong Ha Nguyen (eBay), Quoc Tran-Dinh (UNC Chapel Hill), and Marten van Dijk (Uconn & CWI).

**2020-11-24:**

### 2020

**New paper!**

- "Shuffling Gradient-Based Methods with Momentum" - joint work with Trang H. Tran (Cornell) and Quoc Tran-Dinh (UNC Chapel Hill).

**I will serve as an Area Chair for ICML 2021**.

**I will organize the session "Recent Advances in Stochastic Gradient Algorithms for Machine Learning Applications" at INFORMS Annual Meeting 2020 on November 13, 2020.**

**New paper!**

- "Hogwild! over Distributed Local Data Sets with Linearly Increasing Mini-Batch Sizes" - joint work with Marten van Dijk (Uconn & CWI), Nhuong V. Nguyen (Uconn), Toan N. Nguyen (Uconn), Quoc Tran-Dinh (UNC Chapel Hill), and Phuong Ha Nguyen (eBay).

**Our paper has been accepted for publication to Mathematical Programming**.

- "A Hybrid Stochastic Optimization Framework for Stochastic Composite Nonconvex Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill), Nhan H. Pham (UNC Chapel Hill), and Dzung T. Phan (IBM Research).

**Two papers were accepted to NeurIPS 2020**.

- "Hybrid Variance-Reduced SGD Algorithms for Nonconvex-Concave Minimax Problems" - joint work with Quoc Tran-Dinh (UNC Chapel Hill) and Deyi Liu (UNC Chapel Hill).

- "A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees" - joint work with Haoran Zhu (University of Wisconsin - Madison), Pavankumar Murali (IBM Research), Dzung T. Phan (IBM Research), and Jayant R. Kalagnanam (IBM Research).

**MIT-IBM proposal**"

*Hierarchical Disentangled Representations for Scalable Multi-agent Reinforcement Learning*" (with Cathy Wu (MIT) and Lily Weng (MIT-IBM Lab)) has been accepted for an one year award.

**Our paper has been accepted for publication to Optimization Methods and Software**.

- "Inexact SARAH Algorithm for Stochastic Optimization" - joint work with Katya Scheinberg (Cornell) and Martin Takac (Lehigh).

**One paper was accepted to ICDM 2020**.

- "

__Pruning Deep Neural Networks with L0-constrained Optimization__" - joint work with Dzung T. Phan (IBM Research), Nam H. Nguyen (IBM Research), and Jayant R. Kalagnanam (IBM Research).

**I will serve as an Area Chair for AISTATS 2021**.

**New paper!**

- "Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise" - joint work with Marten van Dijk (Uconn & CWI), Nhuong V. Nguyen (Uconn), Toan N. Nguyen (Uconn), Quoc Tran-Dinh (UNC Chapel Hill), and Phuong Ha Nguyen (Uconn).

**I will serve as an Area Chair for ICLR 2021**.

**New paper!**

- "Hybrid Variance-Reduced SGD Algorithms For Nonconvex-Concave Minimax Problems" - joint work with Quoc Tran-Dinh (UNC Chapel Hill) and Deyi Liu (UNC Chapel Hill).

**I will be joining Journal of Machine Learning Research (JMLR) editorial board**.

**One paper was accepted to ICML 2020**.

- "Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill) and Nhan H. Pham (UNC Chapel Hill).

**Our paper has been accepted for publication to Journal of Machine Learning Research (JMLR)**.

- "ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization" - joint work with Nhan H. Pham (UNC Chapel Hill), Dzung T. Phan (IBM Research), and Quoc Tran-Dinh (UNC Chapel Hill).

**New paper!**

- "Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness" - joint work with Thinh T. Doan (GA Tech), Nhan H. Pham (UNC Chapel Hill), and Justin Romberg (GA Tech).

**New papers!**

- "A Unified Convergence Analysis for Shuffling-Type Gradient Methods" - joint work with Quoc Tran-Dinh (UNC Chapel Hill), Dzung T. Phan (IBM Research), Phuong Ha Nguyen (Uconn), and Marten van Dijk (Uconn).

- "Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill) and Nhan H. Pham (UNC Chapel Hill).

**New paper!**

- "Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning" - joint work with Thinh T. Doan (GA Tech), Nhan H. Pham (UNC Chapel Hill), and Justin Romberg (GA Tech).

**One paper was accepted to AISTATS 2020**.

- "A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning" - joint work with Nhan H. Pham (UNC Chapel Hill), Dzung T. Phan (IBM Research), Phuong Ha Nguyen (Uconn), Marten van Dijk (Uconn), and Quoc Tran-Dinh (UNC Chapel Hill).

**2019-11-06:**

### 2019

**Our paper has been accepted for publication to Journal of Machine Learning Research (JMLR)**.

- "New Convergence Aspects of Stochastic Gradient Algorithms" - joint work with Phuong Ha Nguyen (Uconn), Peter Richtarik (KAUST), Katya Scheinberg (Cornell), Martin Takac (Lehigh), and Marten van Dijk (Uconn).

**I will serve as an Area Chair for ICML 2020**.

**New paper!**

- "BUZz: BUffer Zones for Defending Adversarial Examples in Image Classification" - joint work with Phuong Ha Nguyen (Uconn), Kaleel Mahmood (Uconn), Thanh Nguyen (Iowa State University), and Marten van Dijk (Uconn).

**One paper was accepted to NeurIPS 2019**.

- "Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD" - joint work with Phuong Ha Nguyen (Uconn) and Marten van Dijk (Uconn).

**I will organize a session at INFORMS Annual Meeting 2019 in Seattle, WA on October 21, 2019**.

- "Fast and Provable Nonconvex Optimization Algorithms in Machine Learning" - with Quoc Tran-Dinh (UNC Chapel Hill) and speakers Yi Zhou (IBM Research), Nhan H. Pham (UNC Chapel Hill), and Cesar A. Uribe (MIT).

**New paper!**

- "A Hybrid Stochastic Optimization Framework for Stochastic Composite Nonconvex Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill), Nhan H. Pham (UNC Chapel Hill), and Dzung T. Phan (IBM Research).

**Our paper has been accepted for publication to Journal of Machine Learning Research conditioned on minor revisions**.

- "New Convergence Aspects of Stochastic Gradient Algorithms" - joint work with Phuong Ha Nguyen (Uconn), Peter Richtarik (KAUST), Katya Scheinberg (Cornell), Martin Takac (Lehigh), and Marten van Dijk (Uconn).

**New paper!**

- "Hybrid Stochastic Gradient Descent Algorithms for Stochastic Nonconvex Optimization" - joint work with Quoc Tran-Dinh (UNC Chapel Hill), Nhan H. Pham (UNC Chapel Hill), and Dzung T. Phan (IBM Research).

**Won Elizabeth V. Stout Dissertation Award for my PhD thesis.**

I have won the 2019 P.C. Rossin College of Engineering and Applied Science

*Elizabeth V. Stout Dissertation Award*for my PhD thesis "A Service System with On-Demand Agents, Stochastic Gradient Algorithms and the SARAH Algorithm". Thank for my PhD advisors Katya Scheinberg and Martin Takáč, and my previous advisor Alexander Stolyar. Also, thank for the supports of Marten van Dijk, Luis Vicente, Frank E. Curtis, and George Wilson.

**Two papers were accepted to ICML 2019**.

- "Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD" - joint work with Marten van Dijk (Uconn), Phuong Ha Nguyen (Uconn), and Dzung Phan (IBM Research).

- "PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach" - joint work with Tsui-Wei (Lily) Weng (MIT), Pin-Yu Chen (IBM Research), Mark Squillante (IBM Research), Akhilan Boopathy (MIT), Ivan Oseledets (Skoltech), and Luca Daniel (MIT).

**New paper!**

- "ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization" - joint work with Nhan H. Pham (UNC Chapel Hill), Dzung T. Phan (IBM Research), and Quoc Tran-Dinh (UNC Chapel Hill).

**New paper!**

- "Finite-Sum Smooth Optimization with SARAH" - joint work with Marten van Dijk (Uconn), Dzung T. Phan (IBM Research), Phuong Ha Nguyen (Uconn), Tsui-Wei (Lily) Weng (MIT), and Jayant R. Kalagnanam (IBM Research).