Research theme

Learning with predictions

When should a decision maker trust a prediction?

Algorithms that benefit from accurate advice while limiting the cost of errors. This thread studies consistency, robustness, competitive analysis, and the value of different forms of predictive information.

Explore the research map

Papers

2026AISTATS

Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners

Tinashe Handina, Tongxin Li, Kishan Panaganti, Eric Mazumdar, Adam Wierman

A measure of advice quality connects simulators and payoff predictions to strategic performance. The paper establishes benefits of reliable advice for approximate Stackelberg play and limitations on simultaneously exploiting accurate advice and protecting against inaccurate advice.

Games and equity Predictions Paper
How useful is imperfect advice against an adaptive opponent? game theory learning in games Bayesian games Stackelberg strategies equity public models learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2026IEEE PES International Meeting

PEARL: A Physics-Enhanced Adaptive Residual Learning Framework for PV Modeling

Yikai Lu, Yujie Chen, Tongxin Li

PEARL separates a physical photovoltaic simulator from a learned residual correction. A controlled benchmark compares several machine learning architectures and a coupled modeling baseline, examining accuracy while retaining the physical model as an interpretable reference.

Energy Predictions Paper
Can learned residuals improve physical models of solar generation? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2026POMACS

Prediction-Specific Design of Learning-Augmented Algorithms

Sizhe Li, Nicolas Christianson, Tongxin Li

Strong optimality refines the usual consistency and robustness tradeoff to account for each prediction. A bilevel optimization framework constructs algorithms for ski rental and one max search, with case studies in power management and trading.

Predictions Paper
Can an algorithm be optimal for the particular prediction it receives? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2026IEEE Control Systems Letters

VigilMPC: Certified Online Tube Model Predictive Control for Safe Real-Time Neuromodulation

Yu Mao, Zhichao Liang, Junxiang Zhang, Quanying Liu, Tongxin Li

VigilMPC accepts a predictor update only when a backup plan remains feasible under tightened constraints. Recursive feasibility and constraint satisfaction follow under the tube MPC assumptions. Evaluation uses simulated neural dynamics and a switching benchmark, rather than clinical deployment.

Control Predictions Paper
Can a predictive controller safely update its learned dynamics online? model predictive control MPC stability recursive feasibility distributed control system level synthesis learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2025ACL Findings

Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents

Fanzeng Xia, Hao Liu, Yisong Yue, Tongxin Li

The study identifies a gap between quick preference discovery and sustained exploitation by language agents. LEAD combines LLM reasoning with dueling bandit algorithms to obtain weak and strong regret guarantees, with evaluations under noisy and adversarial prompts.

Agents Predictions Paper
Can language agents learn reliably from pairwise preferences? large language models LLM agents contextual control world models reinforcement learning dueling bandits learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2025ACM e-Energy

Learning-Augmented Online Control for Decarbonizing Water Infrastructures

Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren

LAOC restricts online decisions to safe action sets while exploiting learned predictions for pump scheduling. Analysis characterizes the relationship between safety requirements and operating costs, with a building water supply case study.

Energy Control Predictions Paper
Can learned pump control reduce carbon costs while meeting safety constraints? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization model predictive control MPC stability recursive feasibility distributed control system level synthesis learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2025IEEE Transactions on Transportation Electrification

Out-of-Distribution-Aware Electric Vehicle Charging

Tongxin Li, Chenxi Sun

OOD Charging adapts an awareness radius using temporal difference errors to balance learned scheduling with a robust baseline. Evaluation on ACN data examines behavioral changes during COVID 19 and the resulting distribution shift.

Energy Predictions Control Paper
How should charging schedules respond when user behavior changes? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization model predictive control MPC stability recursive feasibility distributed control system level synthesis
2025CDC

PredSLS: A System-Level Framework for Distributed Predictive Control

Yifei Wu, Jing Yu, Tongxin Li

PredSLS integrates forecasts directly into system level synthesis with locality constraints. Temporal decay of prediction effects supports finite horizon approximations, while spatial and temporal decomposition enable scalable computation across a network.

Control Predictions Paper
How can distributed controllers use predictions with limited communication? model predictive control MPC stability recursive feasibility distributed control system level synthesis learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2025NeurIPS

Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

Chenbei Lu, Zaiwei Chen, Tongxin Li, Chenye Wu, Adam Wierman

A Bayesian value function and Bellman Jensen gap quantify the value of imperfect transition forecasts. BOLA separates offline value learning from online adaptation, with sample efficiency analysis and experiments in synthetic environments and wind energy storage control.

Predictions Agents Energy Paper
How can reinforcement learning use imperfect forecasts beyond one step? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization large language models LLM agents contextual control world models reinforcement learning dueling bandits AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2025Environmental Data Science

Robust machine-learned algorithms for efficient grid operation

Nicolas Christianson, Christopher Yeh, Tongxin Li, Mehdi Hosseini, Mahdi Torabi Rad, Azarang Golmohammadi, Adam Wierman

RobustML combines a learned dispatch algorithm with a bound on worst case cost. A combined cycle cogeneration case study examines dispatch and ramping costs as renewable penetration increases, including performance under distribution shift.

Energy Predictions Control Paper
Can learned dispatch policies remain reliable under distribution shift? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization model predictive control MPC stability recursive feasibility distributed control system level synthesis
2024ICML

Building Socially-Equitable Public Models

Yejia Liu, Jianyi Yang, Pengfei Li, Tongxin Li, Shaolei Ren

The Equitable Objective trains a public predictive model around the outcomes of heterogeneous downstream agents. A policy gradient method and theoretical analysis study a more equitable distribution of performance, beyond optimizing prediction accuracy alone.

Games and equity Predictions Paper
Who benefits when many decision makers share one predictive model? game theory learning in games Bayesian games Stackelberg strategies equity public models learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2024NeurIPS

Disentangling Linear Quadratic Control with Untrusted ML Predictions

Tongxin Li, Hao Liu, Yisong Yue

DISC learns confidence in predictions of latent disturbance components. Competitive analysis covers linear and more general mixing functions, showing how online confidence adaptation can exploit accurate forecasts while maintaining protection against large errors.

Predictions Control Paper
Can a controller learn which components of a forecast to trust? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization model predictive control MPC stability recursive feasibility distributed control system level synthesis
2024NeurIPS

Safe Exploitative Play with Untrusted Type Beliefs

Tongxin Li, Tinashe Handina, Shaolei Ren, Adam Wierman

The paper formalizes a risk and opportunity tradeoff for agents with uncertain beliefs about other players. Upper and lower bounds characterize the Pareto frontier in normal form and stochastic Bayesian games, with numerical illustrations of the tradeoff.

Games and equity Predictions Paper
How much risk comes from exploiting a predicted opponent type? game theory learning in games Bayesian games Stackelberg strategies equity public models learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2023NeurIPS

Anytime-Competitive Reinforcement Learning with Policy Prior

Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren

ACRL constrains cumulative costs relative to a policy prior at each round, rather than only in expectation over episodes. The analysis establishes cost guarantees and regret relative to the constrained optimum, with experiments in carbon aware computing.

Agents Predictions Control Paper
Can reinforcement learning enforce cost protection throughout an episode? large language models LLM agents contextual control world models reinforcement learning dueling bandits learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization model predictive control MPC stability recursive feasibility distributed control system level synthesis
2023NeurIPS

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Tongxin Li, Yiheng Lin, Shaolei Ren, Adam Wierman

Q value predictions expose more information than an opaque policy recommendation. For a single trajectory MDP, the analysis characterizes consistency and robustness tradeoffs and shows how structured advice improves the guarantees available from a robust baseline.

Predictions Agents Paper
Does the structure of advice improve robust decision making? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization large language models LLM agents contextual control world models reinforcement learning dueling bandits
2023IEEE Open Journal of Control Systems

Certifying Black-Box Policies With Stability for Nonlinear Control

Tongxin Li, Ruixiao Yang, Guannan Qu, Yiheng Lin, Adam Wierman, Steven H. Low

Simply blending two stabilizing policies can cause instability. An adaptive confidence policy instead uses approximate model information to certify stability, with competitive guarantees under bounded nonlinearity and evaluations on Cart Pole and charging under distribution shift.

Control Predictions Energy Paper
How can model based advice stabilize a learned nonlinear policy? model predictive control MPC stability recursive feasibility distributed control system level synthesis learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2022NeurIPS

Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity

Yiheng Lin, Yang Hu, Guannan Qu, Tongxin Li, Adam Wierman

A general analysis pipeline converts perturbation bounds for finite horizon control into dynamic regret bounds for MPC. It handles prediction errors in costs, dynamics, and disturbances, and extends the analysis to constrained and nonlinear settings under suitable regularity conditions.

Control Predictions Paper
How do forecast errors translate into regret for MPC? model predictive control MPC stability recursive feasibility distributed control system level synthesis learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2022POMACS

Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions

Tongxin Li, Ruixiao Yang, Guannan Qu, Guanya Shi, Chenkai Yu, Adam Wierman, Steven Low

A confidence parameter governs how much a linear quadratic controller trusts disturbance predictions. Competitive bounds describe the tradeoff between accurate and inaccurate advice, and a self tuning policy adapts confidence online using observed prediction quality.

Predictions Control Paper
Can predictive control balance consistency and robustness automatically? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization model predictive control MPC stability recursive feasibility distributed control system level synthesis
2021IEEE Transactions on Power Systems

Decentralized Provision of Renewable Predictions Within a Virtual Power Plant

Yue Chen, Tongxin Li, Changhong Zhao, Wei Wei

A decentralized prediction provision scheme lets consumers obtain local forecasts and exchange summaries with a virtual power plant. The analysis studies social surplus, convergence, and the demand gap relative to centralized information sharing.

Energy Games and equity Predictions Paper
Can local renewable forecasts support decentralized market coordination? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization game theory learning in games Bayesian games Stackelberg strategies equity public models learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2020POMACS

Competitive Algorithms for the Online Multiple Knapsack Problem with Application to Electric Vehicle Charging

Bo Sun, Ali Zeynali, Tongxin Li, Mohammad Hajiesmaili, Adam Wierman, Danny H. K. Tsang

A general fractional multiple knapsack model captures assignment and rate constraints. An online primal dual algorithm obtains near optimal competitive guarantees and is evaluated using charging traces. This work provides an online allocation foundation without requiring learned predictions.

Predictions Energy Paper
How should limited resources be allocated to requests arriving online? learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2020ACM e-Energy

ORC: An Online Competitive Algorithm for Recommendation and Charging Schedule in Electric Vehicle Charging Network

Bo Sun, Tongxin Li, Steven H. Low, Danny H. K. Tsang

ORC jointly recommends stations and prices while scheduling charging for sequential arrivals. A customizable value function supports competitive guarantees despite uncertainty in arrivals and user choices. Experiments compare operator revenue with benchmark scheduling methods.

Energy Predictions Paper
How can charging recommendations and schedules be coordinated online? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization
2014ISIT

Group Testing with Prior Statistics

Tongxin Li, Chun Lam Chan, Wenhao Huang, Tarik Kaced, Sidharth Jaggi

Adaptive and nonadaptive testing algorithms exploit heterogeneous prior probabilities of defective items. Under the stated independence and sparsity assumptions, their measurement requirements approach information theoretic lower bounds up to explicit constant factors.

Information Predictions Paper
How can prior probabilities reduce the number of group tests? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry learning augmented algorithms algorithms with predictions competitive analysis robustness consistency online optimization

Connected themes

From prediction error to control performance

Trust adaptation in linear quadratic control and perturbation bounds for MPC connect the quality of a forecast to the cost of acting on it. Nonlinear certification adds stability to this picture.

Algorithms guide learned decision makers

Q value advice and imperfect transition forecasts provide structured information for reinforcement learning. LEAD applies a related principle by supporting language agents with dueling bandit algorithms.

Open directions

Certified contextual control

Can contextual and world model updates be certified before they affect a physical system?

Connect language conditioned predictions with local world model guarantees and feasibility checks. An open challenge is preserving safety when both the context and the learned dynamics change during operation.

Prediction quality as a decision resource

Which prediction errors actually matter for the decision being made?

Move from a single forecast accuracy score to guarantees that reflect the prediction, the task, and the affected transitions. This suggests adaptive confidence allocation across sources, horizons, and latent disturbances.

Accountable learning across agents

How should shared models balance efficiency, strategic risk, and equity?

Connect the downstream objectives of public models to robust strategic decision making. A key challenge is evaluating advice when its benefits and failures are distributed unevenly across participating agents.