news

2025
May 10, 2025 Siliang Zeng successfully defended his thesis. Congratulations, Dr. Zeng!

2024
Sep 15, 2024 Group Kayak Activity, with visiting student Chung You Yau from CUHK.

2023
Dec 10, 2023 The group attended NeurIPS 2023.
Nov 25, 2023 Xinwei Zhang Graduation Dinner celebration.
Nov 20, 2023 Xinwei Zhang successfully defended his thesis. Congratulations, Dr. Zhang!
Sep 15, 2023 Group Kayak Activity.

2022
Dec 15, 2022 Group Escape Room Activity.
Oct 15, 2022 Group Hiking Activity at Afton.
May 15, 2022 Xiangyi Chen graduated. Congratulations!

2021
Jun 15, 2021 Our work entitled STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning has been made available online at arXiv. This paper designed a federated learning algorithm which achieves the optimal sample and communication complexity.
May 20, 2021 Our work entitled A near-optimal algorithm for stochastic bilevel optimization via double-momentum has been made available online at arXiv. This paper proposes an algorithm which achieves the best sample complexity for certain class of bi-level optimization problem.
May 15, 2021 Our work entitled “On lower iteration complexity bounds for the convex concave saddle point problems” has been accepted by Mathematical Programming.
May 10, 2021 Our work entitled “RMSprop converges with proper hyper-parameter” has been accepted by ICLR as a spotlight paper.
May 05, 2021 Our work entitled “Decentralized Riemannian Gradient Descent on the Stiefel Manifold” has been accepted by ICML.
Apr 15, 2021 Our work entitled To Supervise or Not To Supervise: How to Effectively Learn Wireless Interference Management Models has been accepted by SPAWC 2021.
Feb 15, 2021 Our work entitled Hybrid Federated Learning: Algorithms and Implementation has been awarded a Best Student Paper Award in the NeurIPS 2020 Workshop on Scalability, Privacy, and Security in Federated Learning (NeurIPS-SpicyFL 2020).

2020
Dec 15, 2020 Our work entitled Asynchronous Advantage Actor Critic: Non-asymptotic Analysis and Linear Speedup has been made available online at arXiv. This paper analyzes the complexity of the popular A3C algorithm.
Dec 10, 2020 Our work entitled Hybrid FL: Algorithms and Implementation has been made available online at arXiv. This paper proposes a new formulation and algorithm for hybrid Federated Learning.
Oct 15, 2020 Our work entitled “Learned conjugate gradient descent network for massive MIMO detection” has been accepted by IEEE TSP.
Sep 20, 2020 Four papers accepted in NeurIPS 2020, with two as spotlights: Understanding Gradient Clipping in Private SGD, SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently, Provably Efficient Neural GTD for Off-Policy Learning, and Distributed Training with Heterogeneous Data.
Sep 10, 2020 Dr. Songtao Lu joined IBM TJ Watson Research Center as a Research Staff.
Aug 20, 2020 Our 2016 paper on ADMM receives a Best Paper Award (Silver) from ICCM.
Aug 15, 2020 Dr. Prashant Khanduri joins the group as a post-doctoral fellow. Welcome!
Jul 20, 2020 Mingyi Hong receives the 2020 IBM Academic Research Award.
Jul 15, 2020 We received the NSF - Intel research award. We propose to understand how to use state-of-the-art optimization and learning tools for wireless communication and networking.
Jun 20, 2020 Two papers accepted by ICML 2020: Min-Max Optimization without Gradients and Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization.
Jun 15, 2020 Our work entitled “Penalty Dual Decomposition Method For Nonsmooth Nonconvex Optimization, Part I and II” has been accepted by IEEE TSP.
Jun 10, 2020 Our overview paper entitled “Non-convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances” has been accepted by IEEE SPM.

2019
Dec 15, 2019 Our work entitled “Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems” has been accepted by IEEE TSP.
Nov 15, 2019 Mingyi Hong visited Princeton University (Host: Yuxin Chen and Jason Lee).
Sep 20, 2019 Three papers accepted by NeurIPS 2019: Min-Max Analysis for Policy Evaluation, Global convergence for actor-critic, and Zeroth-Order Adam method.
Aug 15, 2019 The proposal entitled “Online Modeling of Heterogeneous Autonomy” is funded by AFOSR from 2019-2022.
Jul 15, 2019 The proposal entitled “A Simple and Unifying Optimization Framework for Signal and Information Processing Problems with Min-Max Structures” is funded by NSF from 2019-2022.
Jun 20, 2019 Our work entitled A Deep Learning Method for Online Capacity Estimation of Lithium-Ion Batteries has been accepted by Journal of Energy Storage.
Jun 15, 2019 Our work entitled Distributed Non-Convex First-Order Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms has been accepted by IEEE TSP.
Apr 20, 2019 Our work entitled “On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions” has been accepted by ICML 2019.
Mar 20, 2019 Xinwei Zhang joined the group as a Ph.D. student. Welcome!
Mar 15, 2019 The proposal entitled “Multi-Aspect Intelligence Fusion and Analytics” is funded by ARO from 2019-2022.

2018
Dec 20, 2018 Our work entitled “On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization” has been accepted by ICLR 2019.
Dec 15, 2018 Our work entitled “signSGD via Zeroth-Order Oracle” has been accepted by ICLR 2019.
Nov 15, 2018 Mingyi Hong presented a distinguished lecture about zeroth-order optimization for adversary machine learning at GlobalSIP 2018.
Oct 20, 2018 Haoran Sun received a best student paper prize (third prize) for our paper “Distributed Non-Convex First-Order Optimization” in Asilomar 2018.
Sep 20, 2018 Our work entitled “A Finite Sample Analysis of the Actor-Critic Algorithm” has been accepted by CDC 2018.
Sep 15, 2018 Our work entitled “Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization” has been accepted by NeurIPS 2018.
May 20, 2018 Our work entitled “Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management” has been accepted by IEEE TSP.
May 15, 2018 Our work entitled “Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solutions for Nonconvex Distributed Optimization” has been accepted by ICML 2018.
Apr 15, 2018 Our work entitled “Anchor-Free Correlated Topic Modeling” has been accepted by IEEE TPAMI.
Mar 15, 2018 Our work entitled “Spectral Efficiency Optimization For Millimeter Wave Multi-User MIMO Systems” has been accepted by IEEE JSTSP.
Feb 15, 2018 Mr. Ziping Zhao from Hong Kong University of Science and Technology has joined the group as a visiting student. Welcome!

2017
Nov 20, 2017 Davood Hajinezhad has successfully defended his thesis. Congratulations! After the defense, he will join Duke University for a postdoc.
Nov 15, 2017 Mingyi Hong becomes a member of IEEE MLSP Technical Committee from 2018 - 2020.
Aug 20, 2017 The proposal entitled “Decomposition Framework for Non-convex Nonsmooth Optimization with Applications in Data Analytics” is funded by NSF CMMI from 2017-2021.
Aug 15, 2017 Mingyi Hong is moving to the ECE Department, University of Minnesota as an Assistant Professor in Fall 2017.
May 20, 2017 Two papers accepted by ICML 2017: “Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering” and “A Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks”.
Apr 15, 2017 Songtao Lu has been awarded a Graduate College’s Research Excellence Award. Congratulations!
Jan 15, 2017 Our work entitled “A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization” has been conditionally accepted by IEEE TSP.
Jan 10, 2017 Mingyi Hong becomes a member of IEEE SPCOM Technical Committee from 2017 - 2019.

2016
Nov 15, 2016 Our work entitled “A Distributed, Asynchronous and Incremental Algorithm for Nonconvex Optimization: An ADMM Approach” has been accepted by IEEE TCNS.
Aug 20, 2016 Our work entitled “NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization” has been accepted by NeurIPS 2016.
Aug 15, 2016 Mingyi Hong gave an invited talk in ICCOPT 2016 as a Finalist of the Best Paper Prize for Young Researchers in Continuous Optimization.
Jun 15, 2016 Mingyi Hong gave an invited 2-day short course on modern optimization and decomposition methods in MOA 2016, held at the Chinese Academy of Sciences, Beijing.
May 15, 2016 Our work entitled “On the Linear Convergence of the Alternating Direction Method of Multipliers” has been accepted by Mathematical Programming A.
Jan 15, 2016 Our work entitled “Asynchronous Distributed ADMM for Large-Scale Optimization- Part I and II” has been accepted by IEEE TSP.

2015
Dec 15, 2015 Four papers have been accepted by ICASSP 2016.
Nov 15, 2015 Our work entitled “Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems” has been accepted by SIAM Journal on Optimization.
Sep 15, 2015 Haoran Sun awarded a Presidential Fellowship. Congratulations!
Aug 15, 2015 Our work entitled “A Unified Framework for Large-Scale Block-Structured Optimization Involving Big Data” has been accepted by IEEE Signal Processing Magazine as a Feature Article.
Aug 10, 2015 The proposal entitled “Optimal Provision of Backhaul and Radio Access Networks: A Cross-Network Approach” is funded by NSF CCF.

2014
Sep 15, 2014 Mingyi Hong awarded a Black & Veatch Faculty Fellowship by the College of Engineering, Iowa State.
Sep 10, 2014 Our work entitled “Parallel Successive Convex Approximation for Nonsmooth Nonconvex Optimization” has been accepted by NeurIPS 2014.
Aug 15, 2014 Mingyi Hong started as an Assistant Professor at Iowa State University.
Jun 15, 2014 Our survey paper entitled “Cross-Layer Provisioning of Future Cellular Networks” has been accepted by IEEE Signal Processing Magazine.
May 15, 2014 Our work entitled “Joint Downlink Base Station Association and Power Control for Max-Min Fairness” has been accepted by IEEE JSAC.
Jan 15, 2014 Mingyi Hong has been promoted to Research Assistant Professor.