Yao Ji

Yao Ji

H. Milton Stewart Postdoctoral Fellow

H. Milton Stewart School of Industrial and Systems Engineering

Georgia Institute of Technology · Atlanta, GA

Education & training
    • Parameter-free
    • First / Higher-order
    • Gradient Minimization
    • Variational Inequalities
    • Reinforcement Learning
    • Healthcare Applications
    • Distributed Optimization
    • Statistical Learning
    • Bellman–Harris Process
    • Galton–Watson Process
Beyond research

Operations Researcher

I am an H. Milton Stewart Postdoctoral Fellow in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech mentored by Prof. Guanghui (George) Lan.
My research develops optimization algorithms with optimal convergence rates for machine learning and reinforcement learning. My work centers on the design and complexity analysis of deterministic and stochastic optimization methods, with a current focus on parameter-free algorithms that adapt to unknown problem structure. For machine learning, I develop scalable stochastic methods that require no stepsize tuning. For reinforcement learning, I develop efficient methods for online policy evaluation. Healthcare is a major application domain for both research directions.
Research roadmapA fishbone roadmap whose spine is optimization for machine learning and reinforcement learning. Its directions, from tail to head: distributed statistical learning, completed; parameter-free optimization, completed; optimization for machine learning, in progress; nonconvexity and stochasticity, in progress; machine learning and reinforcement learning for healthcare, completed; long-horizon policy evaluation, completed; structural refinement, a future direction; optimization for reinforcement learning, a future direction; and large-scale post-training, a future direction. Each direction opens a list of its works.Distributedstatistical learningParameter-freeoptimizationOptimizationfor MLNonconvexity andstochasticityML and RLfor healthcareLong-horizonpolicy evaluationStructuralrefinementOptimization for RLLarge-scalepost-training

Observe partially, perform optimally.

Recent News

Available Fall 2026 academic job market Seeking position in operations research.

Seeking a faculty position in operations research, starting Fall 2026.

My work is on the design and analysis of optimization methods, particularly for stochastic problems, drawing on a strong background in probability and stochastic processes. Recent directions include parameter-free and higher-order methods, stochastic variational inequalities, distributed optimization, and reinforcement learning with applications in healthcare.

I would be delighted to connect regarding opportunities.

Major Revision at Mathematical Programming Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates received a major revision invite from Mathematical …

Our paper with Guanghui Lan, Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates, has received a major revision invite from Mathematical Programming, Series A.

Many thanks to the editors and reviewers for their careful reading and helpful comments.

Paper Submitted to the British Journal of Anaesthesia Our paper on transformer-based offline reinforcement learning for perioperative kidney risk management in cardiac …

Our paper Transformer based offline reinforcement learning for coordinated perioperative kidney risk management in cardiac surgery is now under review at the British Journal of Anaesthesia.

This is joint work with Yan Li, Guanghui Lan, Zehua Dong, Shuoling Li, Ilker Guven, Xiaoyu Chen, Lihui Bai, and Jiapeng Huang.

Co-organizing a Session on Stochastic Optimization for RL at INFORMS 2026 Co-organizing Recent Progress in Stochastic Optimization for Reinforcement Learning with Yan Li at the 2026 INFORMS …

I am co-organizing Recent Progress in Stochastic Optimization for Reinforcement Learning with Yan Li (Texas A&M University) at the 2026 INFORMS Annual Meeting.

Join us on Monday, November 2, 2026, at Moscone Center South, Room 212 (Level 2), San Francisco.

Our speakers are Mengmeng Li (EPFL), Yifan Hu (Rutgers University), Zhichao Jia (Georgia Tech), and Laixi Shi (Johns Hopkins University).

Presenting in the INFORMS 2026 Job Market Showcase Presenting Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates in the Stochastic and Decentralized …

I will present Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates in the Stochastic and Decentralized Optimization Job Market Showcase session at the 2026 INFORMS Annual Meeting.

The talk is scheduled for Monday, November 2, 2026, at Moscone Center South, Room 206 (Level 2), San Francisco.

Co-organizing a Session on Stochastic Optimization at INFORMS 2026 Co-organizing New Advances in Stochastic Optimization, Theories and Methodologies with Hongcheng Liu at the 2026 INFORMS …

Together with Hongcheng Liu (University of Florida), I am co-organizing New Advances in Stochastic Optimization: Theories and Methodologies at the 2026 INFORMS Annual Meeting.

The session is scheduled for Sunday, November 1, 2026, at Moscone Center South, Room 209 (Level 2), San Francisco.

The scheduled speakers are Baoyu Zhou (Arizona State University), Tianjiao Li (IBM Research), Grani Adiwena Hanasusanto (University of Illinois Urbana-Champaign), Zhe “Jimmy” Zhang (Purdue University), and Anton Malandii (Brown University).

Attending ColOpt 2026 Attended ColOpt 2026 at Lehigh University, including a funding-agencies session for early-career researchers.

I attended ColOpt 2026 on August 20, 2026, at HST Forum 101, Lehigh University, in Bethlehem, Pennsylvania.

I especially appreciated the funding-agencies session, which offered early-career researchers guidance on funding opportunities and the proposal process.

Many thanks to Lehigh ISE and the organizers, especially Luis Nunes Vicente and Zahra Khatti, for putting this event together.

Talk at MOPTA 2026 Gave a talk on Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates at MOPTA 2026, Lehigh University.

On August 19, 2026, I gave a talk on Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates at MOPTA 2026.

The talk was part of Recent Advances in Stochastic Optimization and Variational Inequalities II, held in Room 85 of the Rauch Business Center at Lehigh University in Bethlehem, Pennsylvania.

Co-organizing Two Sessions at MOPTA 2026 Co-organized and co-chaired two sessions on stochastic optimization and variational inequalities with Tianjiao Li at …

I co-organized and co-chaired two sessions with Tianjiao Li at MOPTA 2026, both held at the Rauch Business Center, Lehigh University, in Bethlehem, Pennsylvania:

  • Recent Advances in Stochastic Optimization and Variational Inequalities I — Tuesday, August 18, Room 91.
  • Recent Advances in Stochastic Optimization and Variational Inequalities II — Wednesday, August 19, Room 85.
Poster at Southern California OR/OM Day Presented a poster on Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates at SoCal OR/OM Day, USC …

On May 29, 2026, I presented a poster on Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates at Southern California OR/OM Day at USC Marshall in Los Angeles.

The poster session was held in the first-floor dining area and adjoining courtyard of Fertitta Hall.

Seminar at Clemson University Gave a seminar at Clemson's School of Mathematical and Statistical Sciences on Stochastic Auto-conditioned Fast Gradient …

I was very happy to give a seminar at Clemson’s School of Mathematical and Statistical Sciences on our recent work, Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates.

I had a wonderful visit, really enjoyed the discussions after the talk, and appreciated the beautiful campus and great weather.

Thank you to Clemson’s School of Mathematical and Statistical Sciences for having me!

Seminar flyer (PDF)

Field Visit to Gwinnett County Wastewater Facility Visited the Gwinnett County wastewater facility with collaborators, marking the start of a new project on reinforcement …

Visited the Gwinnett County wastewater facility with collaborators to learn how wastewater is treated through biological processes and membrane systems.

This visit marks the start of a new project with Civil and Environmental Engineering at Georgia Tech, where we aim to explore the use of reinforcement learning for improving decision-making in complex environmental systems.

Learned a lot from the field trip and excited about the potential of RL in wastewater treatment!

Gwinnett County wastewater facility

Poster Presentation at SCA 2026 in Nashville, Tennessee Presenting our poster on Transformer-Based Patient Response Modeling for Cardiac Surgery-Associated AKI at SCA 2026.

I will be presenting a poster at the SCA 2026 Annual Meeting & Workshops (April 23–26, 2026) on our work: Transformer-Based Patient Response Modeling Across All Perioperative Phases for Cardiac Surgery-Associated Acute Kidney Injury Management.

If you are attending, feel free to stop by and chat!

Chairing a Session at INFORMS Optimization Society Conference 2026 Chairing a session on Accelerated Methods and Sharp Analysis for Nonlinear Optimization at IOS 2026.

I will attend the INFORMS Optimization Society Conference 2026 in Atlanta, GA, and chair the session Accelerated Methods and Sharp Analysis for Nonlinear Optimization.

We have a fantastic speaker lineup:

Come by and say hi if you are interested in any of these fantastic talks!

See you at INFORMS 2025 Presenting a talk on High-Order Accumulative Regularization for Gradient Minimization at INFORMS 2025.

Hi everyone, I will be attending INFORMS 2025 Annual Meeting and presenting our work High-Order Accumulative Regularization for Gradient Minimization in Convex Programming.

You can find the slides here.

See you there!

H. Milton Stewart Postdoctoral Fellow at Georgia Tech Starting my new role as a postdoctoral fellow at Georgia Tech.

I am excited to announce that I will be starting my new role as an H. Milton Stewart Postdoctoral Fellow at Georgia Tech in Fall 2024 advised by Prof. George Lan.

Research Interests and Selected Works

  • Parameter-Free Optimization
  • Stochastic Optimization
  • Higher-Order Optimization
  • Variational Inequalities
  • Reinforcement Learning
  • Healthcare
  • Distributed Optimization

Foundation

Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates

Optimal iteration and sample complexities for parameter-free stochastic acceleration.

  • Parameter-Free Optimization
  • Stochastic Optimization

Yao Ji and Guanghui Lan

Mathematical Programming, Series A

arXiv:2604.06525, 2026

Major revision

Algorithm AR framework for gradient minimization

Require: $S$, a strictly increasing sequence $\{\sigma_s\}_{s=0}^{S}$ with $\sigma_0 = 0$, and an initial point $x_0 \in \mathbb{R}^n$.

  1. for $s = 1,\dots,S$ do
  2. Compute an approximate solution $x_s$ of the proximal subproblem $$x_s \approx \operatorname*{arg\,min}_{x \in \mathbb{R}^n} \Big\{\, f_s(x) := f(x) + \textstyle\sum_{i=1}^{s} \tfrac{\sigma_i - \sigma_{i-1}}{p+\nu}\,\|x - x_{i-1}\|^{p+\nu} \Big\}$$ where $p + \nu \geq 2$, by running a subroutine $\mathcal{A}$ initialized at $x_{s-1}$ for $N_s$ iterations.
  3. end for
  4. Output: $x_S$

High-Order Accumulative Regularization for Gradient Minimization in Convex Programming

Optimal gradient complexity for finding points with small gradients.

  • Parameter-Free Optimization
  • Higher-Order Optimization

Yao Ji and Guanghui Lan

SIAM Journal on Optimization

arXiv:2511.03723, 2025

R&R 2nd round review

Learning and Decision-Making

The SCA 2026 conference poster. Sections cover the background and motivation for cardiac surgery-associated acute kidney injury, the dataset of 108,258 adult cardiac surgery admissions, a reinforcement learning framework formulating perioperative management as sequential decision-making, a transformer model architecture, and results on kernel performance, AKI prediction, and complication prediction, closing with discussion and future work.

Transformer-Based Patient Response Modeling Across All Perioperative Phases for Cardiac Surgery-Associated Acute Kidney Injury Management

Transformer-based modeling of patient response across all perioperative phases, built to support sequential clinical decision-making for cardiac surgery-associated acute kidney injury.

  • Healthcare

Yao Ji, Yan Li, Guanghui Lan, Zehua Dong, Shuoling Li, Ilker Guven, Xiaoyu Chen, Lihui Bai, and Jiapeng Huang

Society of Cardiovascular Anesthesiologists Annual Meeting

Nashville, TN, 2026

Poster

Two motivating settings for distributed optimization. Left: a swarm of UAVs linked by local communication over a mesh network. Right: several hospitals and a university jointly analysing gene expression data over local links. Data stay stored and processed locally at each agent, and the agents work together to solve a common problem.

Distributed Sparse Regression via Penalization

Statistical and computational guarantees for sparse linear regression over a network of agents, formulated as local LASSO losses plus a quadratic penalty on the consensus constraint.

  • Distributed Optimization

Yao Ji, Gesualdo Scutari, Ying Sun, and Harsha Honnappa

Journal of Machine Learning Research

Vol. 24(272), pp. 1–62

2023

Test mean squared error against the number of communications. ATC-DGD with step size 0.06 drops sharply within a few thousand communications and settles on the centralized mean squared error. CTA-DGD with the same step size stalls at the local mean squared error, and CTA-DGD with much smaller step sizes, 0.0001 and 0.00005, decreases only slowly and is still far above the centralized level after 45,000 communications.

Distributed (ATC) Gradient Descent for High Dimension Sparse Regression

First statistical study of adapt-then-combine distributed gradient descent, showing linear convergence to centralized statistical precision with communication growing only logarithmically in the ambient dimension.

  • Distributed Optimization

Yao Ji, Gesualdo Scutari, Ying Sun, and Harsha Honnappa

IEEE Transactions on Information Theory

Vol. 69(8), pp. 5253–5276

2023

Teaching and Service

Teaching Experience

Georgia Institute of Technology, ISyE

Advisor

  • ISyE 4106 Senior Design is the flagship capstone experience of Georgia Tech’s Industrial Engineering undergraduate program. Georgia Tech has described Senior Design as its “most important and most challenging undergraduate course,” and its projects have repeatedly received national recognition, including first-place finishes in the IISE Outstanding ISE Capstone Senior Design Project Competition. Fall 2026

Purdue University, Industrial Engineering

Teaching Assistant

  • IE 335: Operations Research Spring and Fall 2023
  • IE 330: Probability and Statistics in Engineering Fall 2022
  • IE 590: Introduction to Optimization Algorithms (graduate-level) Fall 2022

Beijing Normal University, School of Mathematical Sciences

Co-Lecturer

  • Large Deviation Theory Spring 2018
  • Brownian Motion Fall 2017
  • Random Walk in Random Environment Spring 2017
  • Galton–Watson Branching Process Fall 2016

Teaching Assistant Outstanding Teaching Assistant Award

  • Measure Theory I Fall 2017 and Fall 2018
  • Measure Theory II Spring 2017 and Spring 2018
  • Stochastic Calculus for Finance (graduate-level) Fall 2016

Outreach and Service

Outreach

Service

  • Journal Referee Mathematical Programming
  • Journal Referee SIAM Journal on Optimization
  • Journal Referee Operations Research
  • Journal Referee Journal of the American Statistical Association
  • Journal Referee Stochastic Systems
  • Journal Referee Journal of Global Optimization
  • Journal Referee Journal of Optimization Theory and Applications
  • Journal Referee IEEE Transactions on Automatic Control
  • Conference Reviewer IEEE International Symposium on Information Theory