Research theme

Information and network learning

What information and structure are needed to learn reliably?

Information limits and structured learning, from group testing and communication channels to graph recovery and adaptive graph geometry. These results connect limited measurements to useful representations.

Explore the research map

Papers

2026AAAI

Adaptive Riemannian Graph Neural Networks

Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan

ARGNN learns a node specific Riemannian metric instead of imposing one fixed curvature on an entire graph. A diagonal metric parameterization and geometric regularization support efficient training, with convergence analysis and experiments on homophilic and heterophilic graphs.

Information Paper
How can a graph model adapt to different local geometries? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2026ACM e-Energy

Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning

Xudong Wang, Guoming Tang, Junyu Xue, Srinivasan Keshav, Tongxin Li, Chris Ding

DualNILM jointly recognizes appliance states and identifies energy injected behind the meter. Its transformer architecture combines temporal learning tasks to separate consumption from injections, with evaluation on measured and synthesized datasets.

Energy Information Paper
Can appliances be identified when solar and storage obscure meter readings? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2026CSEE JPES

Quantum Learning and Estimation for Coordinated Operation between Distribution Networks and Energy Communities

Yingrui Zhuang, Lin Cheng, Yuji Cao, Tongxin Li, Ning Qi, Yan Xu, Yue Chen

A hybrid quantum learning model estimates energy community responses to prices, while quantum amplitude estimation supports uncertainty calculations. Numerical studies assess accuracy and resource requirements. Reported timing advantages assume ideal quantum devices rather than deployed hardware.

Energy Information Paper
Can quantum methods assist coordination with limited local information? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2026ICML

World Models in Pieces: Structural Certification for General Agents

Yikai Lu, Yifei Wu, Xinyu Lu, Tongxin Li

Structural certification links performance on compositional goals to local guarantees on world model transitions. The results identify reliable pieces of a model without requiring universal competence, and establish limits on the precision of such guarantees.

Agents Information Paper
Which parts of an agent's world model can support reliable planning? large language models LLM agents contextual control world models reinforcement learning dueling bandits information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2021POMACS

Information Aggregation for Constrained Online Control

Tongxin Li, Yue Chen, Bo Sun, Adam Wierman, Steven Low

Entropic aggregation summarizes a local controller's feasible actions for a remote decision maker. Penalized Predictive Control can approach the regret of full information control under causal invariance and a sufficiently long prediction window.

Control Information Energy Paper
How much feasibility information must a local controller share? model predictive control MPC stability recursive feasibility distributed control system level synthesis information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2020Electric Power Systems Research

Classification of electric vehicle charging time series with selective clustering

Chenxi Sun, Tongxin Li, Steven H. Low, Victor O. K. Li

An iterative procedure extracts and clusters the tail portions of charging curves despite missing observations, variable lengths, scheduling effects, and measurement noise. Experiments on ACN data illustrate how these patterns can support useful charging models.

Energy Information Paper
What battery behavior can be learned from imperfect charging records? AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2020IEEE TSIPN

Learning Graphs From Linear Measurements: Fundamental Trade-Offs and Applications

Tongxin Li, Lucien Werner, Steven H. Low

Bounds for noisy and noiseless graph recovery connect sparsity, graph distributions, and linear measurements. A three stage recovery scheme and practical algorithm are studied on canonical graphs and electrical grid admittance matrices.

Information Energy Paper
What determines the sample complexity of network reconstruction? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2019CDC

Learning Graph Parameters from Linear Measurements: Fundamental Trade-offs and Application to Electric Grids

Tongxin Li, Lucien Werner, Steven H. Low

Information theoretic bounds relate measurement requirements to graph complexity and recovery error. A recovery algorithm estimates topology and parameters from linear measurements, with demonstrations on graph families and electrical grid test cases.

Information Energy Paper
How many measurements are needed to recover a network? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry AI for energy electric vehicle charging demand response renewable energy load forecasting decarbonization
2018ITW

Maximum Likelihood Upper Bounds on the Capacities of Discrete Information Stable Channels

Tongxin Li

The paper derives a maximum likelihood upper bound using optimality conditions for discrete information stable channels. It recovers capacity for selected memoryless channels and develops a counting based bound for the binary deletion channel.

Information Paper
How can channel capacity be bounded through maximum likelihood? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2018ISIT

Quadratically Constrained Channels with Causal Adversaries

Tongxin Li, Bikash Kumar Dey, Sidharth Jaggi, Michael Langberg, Anand D. Sarwate

Capacity is characterized through a sequence of optimization problems under quadratic power constraints. Analytical and numerical bounds show that nonuniform power allocation can outperform uniform allocation in certain signal to noise regimes.

Information Paper
What rates are possible when a jammer observes transmissions causally? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2018IEEE DSW

Robust and Consistent Clustering Recovery via SDP Approaches

Chenxi Sun, Tongxin Li, Victor O. K. Li

A semidefinite programming approach recovers clustering structure in the presence of noise and outliers. The analysis gives conditions for exact recovery and consistency in a Gaussian similarity model, supported by synthetic experiments.

Information Paper
Can clusters be recovered from noisy similarities without knowing their number? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
2016SPAWC

Fundamental limits and achievable strategies for low energy compressed sensing with applications in wireless communication

Tongxin Li, Mayank Bakshi, Pulkit Grover

A communication complexity model measures the energy required to move information during support recovery. Upper and lower bounds show how adaptive message scheduling can reduce decoding energy, with an application to multiuser detection in wireless systems.

Information Paper
What energy is required to decode a sparse signal? information theory graph learning sample complexity compressed sensing graph neural networks Riemannian geometry
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

Recovering structure from limited measurements

Graph recovery estimates electrical network parameters. Charging curve clustering and energy disaggregation recover useful structure from observed behavior and aggregate meter readings.

Open directions

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.

Coordinated low carbon infrastructure

Can distributed energy and water resources adapt together under changing conditions?

Combine local feasibility summaries with distributed predictive control and contextual energy models. Open questions include communication limits, distribution shift, and guarantees across coupled physical networks.