About

Ali Jadbabaie is the Department Head and JR East Professor at the Massachusetts Institute of Technology's Department of Civil and Environmental Engineering. He holds a B.S. degree from Sharif University of Technology, an M.S. from the University of New Mexico, and a Ph.D. from the California Institute of Technology. His research interests encompass network science, network economics, consensus and information aggregation in social networks, and the cooperative control of multi-agent systems. He also focuses on applications of algebraic topology in sensor network coverage and deployment, as well as the analysis, optimization, and control of networked dynamical systems in physics, engineering, and biology. His work includes motion coordination and vision-based control of unmanned air and ground vehicles, robust control, and spectral graph theory. Dr. Jadbabaie is a core faculty member at the Institute for Data, Systems and Society and a faculty/PI at the Laboratory for Information and Decision Systems, contributing significantly to advancing knowledge in these areas.

Research topics

• Computer Science
• Artificial Intelligence
• Political Science
• Business
• Mathematics
• Economics
• Econometrics
• Medicine
• Geography
• Mathematical analysis
• Pure mathematics
• Actuarial science
• Engineering
• Operations research
• Machine Learning
• Environmental health
• Statistics
• World Wide Web
• Data science
• Meteorology
• Discrete mathematics
• Combinatorics

Selected publications

• Random walks on simplicial complexes and the normalized Hodge 1-Laplacian

  SIAM Review · 217 citations

  Senior authorCorresponding
  • Mathematics
  • Combinatorics
  • Discrete mathematics

  <p>Using graphs to model pairwise relationships between entities is a ubiquitous framework for studying complex systems and data. Simplicial complexes extend this dyadic model of graphs to polyadic relationships and have emerged as a model for multinode relationships occurring in many complex systems. For instance, biological interactions occur between sets of molecules and communication systems include group messages that are not pairwise interactions. While Laplacian dynamics have been intensely studied for graphs, corresponding notions of Laplacian dynamics beyond the node-space have so far remained largely unexplored for simplicial complexes. In particular, diffusion processes such as random walks and their relationship to the graph Laplacian---which underpin many methods of network analysis, including centrality measures, community detection, and contagion models---lack a proper correspondence for general simplicial complexes.</p>\n\n<p>Focusing on coupling between edges, we generalize the relationship between the normalized graph Laplacian and random walks on graphs by devising an appropriate normalization for the Hodge Laplacian---the generalization of the graph Laplacian for simplicial complexes---and relate this to a random walk on edges. Importantly, these random walks are intimately connected to the topology of the simplicial complex, just as random walks on graphs are related to the topology of the graph. This serves as a foundational step toward incorporating Laplacian-based analytics for higher-order interactions. We demonstrate how to use these dynamics for data analytics that extract information about the edge-space of a simplicial complex that complements and extends graph-based analysis. Specifically, we use our normalized Hodge Laplacian to derive spectral embeddings for examining trajectory data of ocean drifters near Madagascar and also develop a generalization of personalized PageRank for the edge-space of simplicial complexes to analyze a book copurchasing dataset.</p>

  DOI

• Online Learning for Supervisory Switching Control

  ArXiv.org · 2026-03-16

  articleOpen accessSenior author

  We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy the best controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such as system stability, which preclude testing potentially unstable controllers. To bridge this gap, we propose a novel, non-asymptotic analysis of supervisory control that adapts multi-armed bandit algorithms to a control-theoretic setting. The proposed data-driven algorithm evaluates candidate controllers via scoring criteria that leverage system observability to isolate the effects of state history, enabling both detection of destabilizing controllers and accurate system identification. We present two algorithmic variants with dimension-free, finite-time guarantees, where each identifies the most suitable controller in $\mathcal{O}(N \log N)$ steps, while simultaneously achieving finite $L_2$-gain with respect to system disturbances.

  PublisherOA PDF

• Online Learning for Supervisory Switching Control

  arXiv (Cornell University) · 2026-03-16

  preprintOpen accessSenior author

  We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy the best controller for the unknown system by periodically selecting among a collection of $N$ candidate controllers, some of which may destabilize the underlying system. While classical estimator-based supervisory control guarantees asymptotic stability, it lacks quantitative finite-time performance bounds. Conversely, current non-asymptotic methods in both online learning and system identification require restrictive assumptions that are incompatible in a control setting, such as system stability, which preclude testing potentially unstable controllers. To bridge this gap, we propose a novel, non-asymptotic analysis of supervisory control that adapts multi-armed bandit algorithms to a control-theoretic setting. The proposed data-driven algorithm evaluates candidate controllers via scoring criteria that leverage system observability to isolate the effects of state history, enabling both detection of destabilizing controllers and accurate system identification. We present two algorithmic variants with dimension-free, finite-time guarantees, where each identifies the most suitable controller in $\mathcal{O}(N \log N)$ steps, while simultaneously achieving finite $L_2$-gain with respect to system disturbances.

  PublisherDOI

• Unbiased Regression-Adjusted Estimation of Average Treatment Effects in Randomized Controlled Trials

  ArXiv.org · 2025-11-05

  preprintOpen access

  This article introduces a leave-one-out regression adjustment (LOORA) for estimating average treatment effects in randomized controlled trials. In finite samples, LOORA removes the bias of conventional regression adjustment and yields exact variance formulas for regression-adjusted Horvitz-Thompson and difference-in-means estimators. Ridge regularization curbs the influence of high-leverage observations, improving stability and precision in small samples. In large samples, LOORA matches the variance of the regression-adjusted estimator in Lin (2013) while remaining exactly unbiased. Two within-subject experimental applications, each providing a realistic joint distribution of potential outcomes as ground truth, show that LOORA removes substantial bias and achieves confidence interval coverage close to the nominal level.

  PublisherOA PDFDOI

• A game-theoretic model of misinformation spread on social networks

  Games and Economic Behavior · 2025-07-30 · 2 citations

  articleSenior authorCorresponding
  PublisherDOI

• Is Your Conditional Diffusion Model Actually Denoising?

  arXiv (Cornell University) · 2025-12-21

  preprintOpen accessSenior author

  We study the inductive biases of diffusion models with a conditioning-variable, which have seen widespread application as both text-conditioned generative image models and observation-conditioned continuous control policies. We observe that when these models are queried conditionally, their generations consistently deviate from the idealized "denoising" process upon which diffusion models are formulated, inducing disagreement between popular sampling algorithms (e.g. DDPM, DDIM). We introduce Schedule Deviation, a rigorous measure which captures the rate of deviation from a standard denoising process, and provide a methodology to compute it. Crucially, we demonstrate that the deviation from an idealized denoising process occurs irrespective of the model capacity or amount of training data. We posit that this phenomenon occurs due to the difficulty of bridging distinct denoising flows across different parts of the conditioning space and show theoretically how such a phenomenon can arise through an inductive bias towards smoothness.

  PublisherDOI

• Tracking Truth with Liquid Democracy

  Management Science · 2025-01-08 · 2 citations

  article

  The dynamics of random transitive delegations on a graph are of particular interest when viewed through the lens of an emerging voting paradigm: liquid democracy. This paradigm allows voters to choose between directly voting and transitively delegating their votes to other voters so that those selected cast a vote weighted by the number of delegations that they received. In the epistemic setting, where voters decide on a binary issue for which there is a ground truth, previous work showed that a few voters may amass such a large amount of influence that liquid democracy is less likely to identify the ground truth than direct voting. We quantify the amount of permissible concentration of power and examine more realistic delegation models, showing that they behave well by ensuring that (with high probability) there is a permissible limit on the maximum number of delegations received. Our theoretical results demonstrate that the delegation process is similar to well-known processes on random graphs that are sufficiently bounded for our purposes. Along the way, we prove new bounds on the size of the largest component in an infinite Pólya urn process, which may be of independent interest. In addition, we empirically validate the theoretical results, running six experiments (for a total of N = 168 participants, 62 delegation graphs, and over 11,000 votes collected). We find that empirical delegation behaviors meet the conditions for our positive theoretical guarantees. Overall, our work alleviates concerns raised about liquid democracy and bolsters the case for the applicability of this emerging paradigm. This paper was accepted by Martin Bichler, market design, platform, and demand analytics. Funding: This work was supported by the Michael Hammer Fellowship, the Office of Naval Research [2016 Vannevar Bush Faculty Fellowship, 2020 ONR Vannevar Bush Faculty Fellowship, and Grant N00014-20-1-2488], the Office of Secretary of Defense [Grants ARO MURI W911NF-19-0217 and ARO W911NF-17-1-0592], Simons [Investigator Award 622132], the Open Philanthropy Foundation, and the National Science Foundation [Grants IIS-178108, CCF-1733556, CCF-1918421, CCF-2007080, IIS-1703846, and IIS-2024287]. J. Y. Halpern was supported by a grant from the Cooperative AI Foundation [ARO Grant W911NF-22-1-0061]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.02470 .

  PublisherDOI

• Variance-reduced Clipping for Non-convex Optimization

  2025-03-12 · 1 citations

  articleSenior author

  Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the smoothness of the training objective along its trajectory when trained with gradient clipping. That is, the smoothness grows with the gradient norm. This is in clear contrast to the wellestablished assumption in folklore non-convex optimization, a.k.a. L–smoothness, where the smoothness is assumed to be bounded by a constant L globally. The recently introduced (L<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</inf>, L<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</inf>)– smoothness is a more relaxed notion that captures such behavior in non-convex optimization. It has been shown that under this relaxed smoothness assumption, SGD with clipping requires $\mathcal{O}\left( {{ \in ^{ - 4}}} \right)$ stochastic gradient computations to find an ϵ–stationary solution. In this paper, we employ a variance reduction technique, namely Spider, and demonstrate that for a carefully designed learning rate, this complexity is improved to $\mathcal{O}\left( {{ \in ^{ - 3}}} \right)$ which is order-optimal. Moreover, when the objective is the average of n components, we improve the existing $\mathcal{O}\left( {n{ \in ^{ - 2}}} \right)$ gradient complexity to $\mathcal{O}\left( {\sqrt n { \in ^{ - 2}} + n} \right)$, which is order-optimal as well.

  PublisherDOI

• Fast Tensor Completion via Approximate Richardson Iteration

  ArXiv.org · 2025-02-13

  preprintOpen accessSenior author

  We study tensor completion (TC) through the lens of low-rank tensor decomposition (TD). Many TD algorithms use fast alternating minimization methods to solve highly structured linear regression problems at each step (e.g., for CP, Tucker, and tensor-train decompositions). However, such algebraic structure is often lost in TC regression problems, making direct extensions unclear. This work proposes a novel lifting method for approximately solving TC regression problems using structured TD regression algorithms as blackbox subroutines, enabling sublinear-time methods. We analyze the convergence rate of our approximate Richardson iteration-based algorithm, and our empirical study shows that it can be 100x faster than direct methods for CP completion on real-world tensors.

  PublisherOA PDFDOI

• Network and Risk Analysis of Surety Bonds

  ArXiv.org · 2025-11-07

  preprintOpen access

  Surety bonds are financial agreements between a contractor (principal) and obligee (project owner) to complete a project. However, most large-scale projects involve multiple contractors, creating a network and introducing the possibility of incomplete obligations to propagate and result in project failures. Typical models for risk assessment assume independent failure probabilities within each contractor. However, we take a network approach, modeling the contractor network as a directed graph where nodes represent contractors and project owners and edges represent contractual obligations with associated financial records. To understand risk propagation throughout the contractor network, we extend the celebrated Friedkin-Johnsen model and introduce a stochastic process to simulate principal failures across the network. From a theoretical perspective, we show that under natural monotonicity conditions on the contractor network, incorporating network effects leads to increases in the average risk for the surety organization. We further use data from a partnering insurance company to validate our findings, estimating an approximately 2% higher exposure when accounting for network effects.

  PublisherOA PDFDOI

Recent grants

• CAREER: Distributed Coordination Strategies for Mobile Autonomous Agents

  NSF · $400k · 2004–2010

• Topological Methods for Distributed Coverage Problems in Mobile Sensing Networks

  NSF · $270k · 2007–2012

Frequent coauthors

• George J. Pappas

  79 shared

• Amir Ajorlou

  62 shared

• Víctor M. Preciado

  University of Pennsylvania

  51 shared

• Alireza Tahbaz-Salehi

  Northwestern University

  51 shared

• Vasileios Tzoumas

  43 shared

• Devavrat Shah

  40 shared

• Shahin Shahrampour

  36 shared

• Suvrit Sra

  36 shared

Education

• Ph.D., Electrical Engineering and Computer Science

  Massachusetts Institute of Technology

  2006

• M.S., Electrical Engineering and Computer Science

  Massachusetts Institute of Technology

  2002

• B.S., Electrical Engineering

  Sharif University of Technology

  1999