no code implementations • ICML 2020 • Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Suvrit Sra, Ali Jadbabaie
Therefore, we introduce the notion of (delta, epsilon)-stationarity, a generalization that allows for a point to be within distance delta of an epsilon-stationary point and reduces to epsilon-stationarity for smooth functions.
no code implementations • 11 Apr 2024 • Haoyuan Sun, Ali Jadbabaie
The focus of this paper is on linear system identification in the setting where it is known that the underlying partially-observed linear dynamical system lies within a finite collection of known candidate models.
no code implementations • 25 Mar 2024 • Mahyar JafariNodeh, Amir Ajorlou, Ali Jadbabaie
Agents can share their learning experience with their peers by taking actions observable to them, with values from a finite feasible set of states.
no code implementations • 26 Oct 2023 • Jennifer Tang, Aviv Adler, Amir Ajorlou, Ali Jadbabaie
To address this, Jadbabaie et al. formulated the interacting P\'olya urn model of opinion dynamics under social pressure and studied it on complete-graph social networks using an aggregate estimator, and found that their estimator converges to the inherent beliefs unless majority pressure pushes the network to consensus.
1 code implementation • 2 Oct 2023 • Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra
Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics.
no code implementations • 18 Aug 2023 • Jennifer Tang, Aviv Adler, Amir Ajorlou, Ali Jadbabaie
To study this, the interacting Polya urn model was introduced by Jadbabaie et al., in which each agent has two kinds of opinion: inherent beliefs, which are hidden from the other agents and fixed; and declared opinions, which are randomly sampled at each step from a distribution which depends on the agent's inherent belief and her neighbors' past declared opinions (the social pressure component), and which is then communicated to their neighbors.
no code implementations • NeurIPS 2023 • Xinyi Wu, Amir Ajorlou, Zihui Wu, Ali Jadbabaie
Oversmoothing in Graph Neural Networks (GNNs) refers to the phenomenon where increasing network depth leads to homogeneous node representations.
no code implementations • 25 May 2023 • Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra
Under this notion, we then analyze algorithms that find approximate flat minima efficiently.
1 code implementation • 2 Mar 2023 • Amirhossein Reisizadeh, Haochuan Li, Subhro Das, Ali Jadbabaie
This is in clear contrast to the well-established assumption in folklore non-convex optimization, a. k. a.
no code implementations • 21 Dec 2022 • Xinyi Wu, Zhengdao Chen, William Wang, Ali Jadbabaie
Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs).
no code implementations • 17 Oct 2022 • Kwangjun Ahn, Zakaria Mhammedi, Horia Mania, Zhang-Wei Hong, Ali Jadbabaie
Recent approaches to data-driven MPC have used the simplest form of imitation learning known as behavior cloning to learn controllers that mimic the performance of MPC by online sampling of the trajectories of the closed-loop MPC system.
no code implementations • 3 Jul 2022 • Haochuan Li, Farzan Farnia, Subhro Das, Ali Jadbabaie
In this paper, we aim to bridge this gap by analyzing the \emph{local convergence} of general \emph{nonconvex-nonconcave} minimax problems.
no code implementations • 20 Jun 2022 • Şerban Sabău, Andrei Sperilă, Cristian Oară, Ali Jadbabaie
We study a class of dynamical networks modeled by linear and time-invariant systems which are described by state-space realizations.
no code implementations • 16 Jun 2022 • Romain Cosson, Ali Jadbabaie, Anuran Makur, Amirhossein Reisizadeh, Devavrat Shah
When $r \ll p$, these complexities are smaller than the known complexities of $\mathcal{O}(p \log(1/\epsilon))$ and $\mathcal{O}(p/\epsilon^2)$ of {\gd} in the strongly convex and non-convex settings, respectively.
no code implementations • 6 Jun 2022 • Farzan Farnia, Amirhossein Reisizadeh, Ramtin Pedarsani, Ali Jadbabaie
In this paper, we focus on this problem and propose a novel personalized Federated Learning scheme based on Optimal Transport (FedOT) as a learning algorithm that learns the optimal transport maps for transferring data points to a common distribution as well as the prediction model under the applied transport map.
no code implementations • 3 Apr 2022 • Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian
In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model.
no code implementations • 29 Mar 2022 • Ali Jadbabaie, Arnab Sarker, Devavrat Shah
Successful predictive modeling of epidemics requires an understanding of the implicit feedback control strategies which are implemented by populations to modulate the spread of contagion.
no code implementations • 7 Jan 2022 • Arnab Sarker, Ali Jadbabaie, Devavrat Shah
The model represents time series of cases and fatalities as a mixture of Gaussian curves, providing a flexible function class to learn from data compared to traditional mechanistic models.
no code implementations • 6 Jan 2022 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
Under some assumptions on the loss function, e. g., strong convexity in parameter, $\eta$-H\"older smoothness in data, etc., we prove that the federated oracle complexity of FedLRGD scales like $\phi m(p/\epsilon)^{\Theta(d/\eta)}$ and that of FedAve scales like $\phi m(p/\epsilon)^{3/4}$ (neglecting sub-dominant factors), where $\phi\gg 1$ is a "communication-to-computation ratio," $p$ is the parameter dimension, and $d$ is the data dimension.
no code implementations • 29 Dec 2021 • Ali Jadbabaie, Horia Mania, Devavrat Shah, Suvrit Sra
We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system.
no code implementations • 16 Dec 2021 • Şerban Sabău, Andrei Sperilă, Cristian Oară, Ali Jadbabaie
In this paper, we discuss a distributed control architecture, aimed at networks with linear and time-invariant dynamics, which is amenable to convex formulations for controller design.
no code implementations • 12 Oct 2021 • Jingzhao Zhang, Haochuan Li, Suvrit Sra, Ali Jadbabaie
This work examines the deep disconnect between existing theoretical analyses of gradient-based algorithms and the practice of training deep neural networks.
no code implementations • 22 Apr 2021 • Ali Jadbabaie, Anuran Makur, Elchanan Mossel, Rabih Salhab
At each time step, agents broadcast their declared opinions on a social network, which are governed by the agents' inherent opinions and social pressure.
no code implementations • NeurIPS 2021 • Haochuan Li, Yi Tian, Jingzhao Zhang, Ali Jadbabaie
We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minimization variable, and strongly concave in the maximization variable.
no code implementations • 12 Mar 2021 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We propose matrix norm inequalities that extend the Recht-R\'e (2012) conjecture on a noncommutative AM-GM inequality by supplementing it with another inequality that accounts for single-shuffle, which is a widely used without-replacement sampling scheme that shuffles only once in the beginning and is overlooked in the Recht-R\'e conjecture.
no code implementations • 1 Jan 2021 • Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
In particular, standard results on optimal convergence rates for stochastic optimization assume either there exists a uniform bound on the moments of the gradient noise, or that the noise decays as the algorithm progresses.
no code implementations • NeurIPS 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
no code implementations • 20 Nov 2020 • James Z. Hare, Cesar A. Uribe, Lance Kaplan, Ali Jadbabaie
Non-Bayesian social learning theory provides a framework that solves this problem in an efficient manner by allowing the agents to sequentially communicate and update their beliefs for each hypothesis over the network.
no code implementations • 4 Nov 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In contrast, we demonstrate that when the loss function is smooth in the data, we can learn the oracle at every iteration and beat the oracle complexities of both GD and SGD in important regimes.
no code implementations • 7 Jul 2020 • César A. Uribe, Ali Jadbabaie
We propose a distributed, cubic-regularized Newton method for large-scale convex optimization over networks.
no code implementations • 18 Jun 2020 • Farzan Farnia, William Wang, Subhro Das, Ali Jadbabaie
Motivated by optimal transport theory, we design the zero-sum game in GAT-GMM using a random linear generator and a softmax-based quadratic discriminator architecture, which leads to a non-convex concave minimax optimization problem.
no code implementations • NeurIPS 2020 • Amirhossein Reisizadeh, Farzan Farnia, Ramtin Pedarsani, Ali Jadbabaie
In such settings, the training data is often statistically heterogeneous and manifests various distribution shifts across users, which degrades the performance of the learnt model.
no code implementations • 15 Jun 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
no code implementations • 8 Jun 2020 • Jingzhao Zhang, Hongzhou Lin, Subhro Das, Suvrit Sra, Ali Jadbabaie
We study oracle complexity of gradient based methods for stochastic approximation problems.
no code implementations • 10 Feb 2020 • Jingzhao Zhang, Hongzhou Lin, Stefanie Jegelka, Ali Jadbabaie, Suvrit Sra
In particular, we study the class of Hadamard semi-differentiable functions, perhaps the largest class of nonsmooth functions for which the chain rule of calculus holds.
no code implementations • 28 Sep 2019 • Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, Ramtin Pedarsani
Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized.
no code implementations • 9 Sep 2019 • James Z. Hare, Cesar A. Uribe, Lance Kaplan, Ali Jadbabaie
Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a social network.
no code implementations • NeurIPS 2019 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least as good as the best linear predictor.
1 code implementation • ICLR 2020 • Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie
We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks.
no code implementations • NeurIPS 2019 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We also prove that width $\Theta(\sqrt{N})$ is necessary and sufficient for memorizing $N$ data points, proving tight bounds on memorization capacity.
no code implementations • ICLR 2019 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
In the benign case, we solve one equality constrained QP, and we prove that projected gradient descent solves it exponentially fast.
no code implementations • NeurIPS 2018 • Aryan Mokhtari, Asuman Ozdaglar, Ali Jadbabaie
We propose a generic framework that yields convergence to a second-order stationary point of the problem, if the convex set $\mathcal{C}$ is simple for a quadratic objective function.
no code implementations • 5 Sep 2018 • Hoi-To Wai, Santiago Segarra, Asuman E. Ozdaglar, Anna Scaglione, Ali Jadbabaie
The paper shows that communities can be detected by applying a spectral method to the covariance matrix of graph signals.
1 code implementation • 13 Jul 2018 • Michael T. Schaub, Austin R. Benson, Paul Horn, Gabor Lippner, Ali Jadbabaie
Simplicial complexes, a mathematical object common in topological data analysis, have emerged as a model for multi-nodal interactions that occur in several complex systems; for example, biological interactions occur between a set of molecules rather than just two, and communication systems can have group messages and not just person-to-person messages.
Social and Information Networks Discrete Mathematics Algebraic Topology Physics and Society
no code implementations • NeurIPS 2018 • Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra, Ali Jadbabaie
We study gradient-based optimization methods obtained by directly discretizing a second-order ordinary differential equation (ODE) related to the continuous limit of Nesterov's accelerated gradient method.
no code implementations • 2 Apr 2018 • Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas
The objective of this paper is to focus on resilient matroid-constrained problems arising in control and sensing but in the presence of sensor and actuator failures.
no code implementations • 21 Mar 2018 • Vasileios Tzoumas, Ali Jadbabaie, George J. Pappas
In this paper, we provide the first scalable algorithm, that achieves the following characteristics: system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks, deletions, or failures; adaptiveness, i. e., at each time step, the algorithm selects system elements based on the history of inflicted attacks, deletions, or failures; and provable approximation performance, i. e., the algorithm guarantees for monotone objective functions a solution close to the optimal.
2 code implementations • 20 Feb 2018 • Austin R. Benson, Rediet Abebe, Michael T. Schaub, Ali Jadbabaie, Jon Kleinberg
Networks provide a powerful formalism for modeling complex systems by using a model of pairwise interactions.
no code implementations • ICLR 2019 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Our results thus indicate that in general "no spurious local minima" is a property limited to deep linear networks, and insights obtained from linear networks may not be robust.
no code implementations • ICLR 2018 • Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss.
no code implementations • 12 May 2017 • Jan Hązła, Ali Jadbabaie, Elchanan Mossel, M. Amin Rahimian
We study the computations that Bayesian agents undertake when exchanging opinions over a network.
no code implementations • 21 Feb 2017 • Shahin Shahrampour, Ali Jadbabaie
We formulate this problem as a distributed online optimization where agents communicate with each other to track the minimizer of the global loss.
no code implementations • 27 Nov 2016 • M. Amin Rahimian, Ali Jadbabaie
While such repeated applications of the Bayes' rule in networks can become computationally intractable, in this paper, we show that in the canonical cases of directed star, circle or path networks and their combinations, one can derive a class of memoryless update rules that replicate that of a single Bayesian agent but replace the self beliefs with the beliefs of the neighbors.
no code implementations • 10 Nov 2016 • M. Amin Rahimian, Ali Jadbabaie
In each case we rely on an aggregation scheme to combine the observations of all agents; moreover, when the agents receive streams of data over time, we modify the update rules to accommodate the most recent observations.
no code implementations • 9 Sep 2016 • Shahin Shahrampour, Ali Jadbabaie
A network of agents aim to track the minimizer of a global time-varying convex function.
no code implementations • 16 Mar 2016 • Aryan Mokhtari, Shahin Shahrampour, Ali Jadbabaie, Alejandro Ribeiro
In this paper, we address tracking of a time-varying parameter with unknown dynamics.
no code implementations • 2 Mar 2016 • Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie
To this end, we use a notion of dynamic regret which suits the online, non-stationary nature of the problem.
no code implementations • 30 Sep 2015 • Mohammad Amin Rahimian, Ali Jadbabaie
We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents' beliefs are formed.
no code implementations • 14 Sep 2015 • Mohammad Amin Rahimian, Shahin Shahrampour, Ali Jadbabaie
Each agent might not be able to distinguish the true state based only on her private observations.
no code implementations • 11 Mar 2015 • Shahin Shahrampour, Mohammad Amin Rahimian, Ali Jadbabaie
A network of agents attempt to learn some unknown state of the world drawn by nature from a finite set.
no code implementations • 26 Jan 2015 • Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour, Karthik Sridharan
Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees.
no code implementations • 30 Sep 2014 • Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie
In contrast to the existing literature which focuses on asymptotic learning, we provide a finite-time analysis.
no code implementations • NeurIPS 2013 • Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie
Based on the decomposition of the global loss function, we introduce two update mechanisms, each of which generates an estimate of the true state.
no code implementations • 10 Sep 2013 • Shahin Shahrampour, Ali Jadbabaie
When the true state is globally identifiable, and the network is connected, we prove that agents eventually learn the true parameter using a randomized gossip scheme.