no code implementations • 2 Dec 2006 • Elchanan Mossel, Sebastien Roch
Here we prove a conjecture of KKT: we show that the function $\sigma(S)$ is submodular under the assumptions above.
Probability Computer Science and Game Theory Social and Information Networks
no code implementations • 3 Feb 2010 • Elchanan Mossel, Noah Olsman, Omer Tamuz
Finally, we show that on trees and on distance transitive-graphs the process converges after $D$ steps, and that it preserves privacy, so that agents learn very little about the private signal of most other agents, despite the efficient aggregation of information.
no code implementations • 24 Jun 2013 • Florent Krzakala, Cristopher Moore, Elchanan Mossel, Joe Neeman, Allan Sly, Lenka Zdeborová, Pan Zhang
Spectral algorithms are classic approaches to clustering and community detection in networks.
no code implementations • 13 Jul 2013 • Varun Kanade, Elchanan Mossel
The theory of learning under the uniform distribution is rich and deep, with connections to cryptography, computational complexity, and the analysis of boolean functions to name a few areas.
no code implementations • 12 Mar 2015 • Elchanan Mossel, Mesrob I. Ohannessian
The probability of this event is referred to as the "missing mass".
no code implementations • 21 Apr 2015 • Elchanan Mossel, Sebastien Roch
We consider the reconstruction of a phylogeny from multiple genes under the multispecies coalescent.
no code implementations • 10 Aug 2015 • Elchanan Mossel, Jiaming Xu
There has been a recent interest in understanding the power of local algorithms for optimization and inference problems on sparse graphs.
no code implementations • 10 Sep 2015 • Elchanan Mossel, Jiaming Xu
There is a recent surge of interest in identifying the sharp recovery thresholds for cluster recovery under the stochastic block model.
no code implementations • 29 Dec 2016 • Elchanan Mossel
It is argued that deep learning is efficient for data that is generated from hierarchal generative models.
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 • 13 Jul 2017 • Gautam Dasarathy, Elchanan Mossel, Robert Nowak, Sebastien Roch
As a corollary, we also obtain a new identifiability result of independent interest: for any species tree with $n \geq 3$ species, the rooted species tree can be identified from the distribution of its unrooted weighted gene trees even in the absence of a molecular clock.
no code implementations • 5 Nov 2017 • Vishesh Jain, Frederic Koehler, Elchanan Mossel
One exception is recent results by Risteski (2016) who considered dense graphical models and showed that using variational methods, it is possible to find an $O(\epsilon n)$ additive approximation to the log partition function in time $n^{O(1/\epsilon^2)}$ even in a regime where correlation decay does not hold.
no code implementations • 16 Feb 2018 • Vishesh Jain, Frederic Koehler, Elchanan Mossel
Results in graph limit literature by Borgs, Chayes, Lov\'asz, S\'os, and Vesztergombi show that for Ising models on $n$ nodes and interactions of strength $\Theta(1/n)$, an $\epsilon$ approximation to $\log Z_n / n$ can be achieved by sampling a randomly induced model on $2^{O(1/\epsilon^2)}$ nodes.
no code implementations • 16 Feb 2018 • Vishesh Jain, Frederic Koehler, Elchanan Mossel
The mean field approximation to the Ising model is a canonical variational tool that is used for analysis and inference in Ising models.
no code implementations • 25 May 2018 • Guy Bresler, Frederic Koehler, Ankur Moitra, Elchanan Mossel
This hardness result is based on a sharp and surprising characterization of the representational power of bounded degree RBMs: the distribution on their observed variables can simulate any bounded order MRF.
no code implementations • NeurIPS 2018 • Yash Deshpande, Andrea Montanari, Elchanan Mossel, Subhabrata Sen
We provide the first information theoretic tight analysis for inference of latent community structure given a sparse graph along with high dimensional node covariates, correlated with the same latent communities.
no code implementations • 26 Jul 2018 • Elchanan Mossel, Jiaming Xu
We study a well known noisy model of the graph isomorphism problem.
1 code implementation • 8 Oct 2018 • Dean Eckles, Elchanan Mossel, M. Amin Rahimian, Subhabrata Sen
To model the trade-off between long and short edges we analyze the rate of spread over networks that are the union of circular lattices and random graphs on $n$ nodes.
Social and Information Networks Probability Physics and Society 91D30, 05C80
1 code implementation • 10 May 2019 • Dean Eckles, Hossein Esfandiari, Elchanan Mossel, M. Amin Rahimian
We study the task of selecting $k$ nodes, in a social network of size $n$, to seed a diffusion with maximum expected spread size, under the independent cascade model with cascade probability $p$.
Social and Information Networks Computational Complexity Probability Physics and Society
no code implementations • 24 May 2019 • Vishesh Jain, Frederic Koehler, Jingbo Liu, Elchanan Mossel
The analysis of Belief Propagation and other algorithms for the {\em reconstruction problem} plays a key role in the analysis of community detection in inference on graphs, phylogenetic reconstruction in bioinformatics, and the cavity method in statistical physics.
no code implementations • 24 Apr 2020 • Anindya De, Elchanan Mossel, Joe Neeman
Using our techniques, we also obtain a fully noise tolerant tester with the same query complexity for any class $\mathcal{C}$ of linear $k$-juntas with surface area bounded by $s$.
no code implementations • 8 May 2020 • Younhun Kim, Elchanan Mossel, Govind Ramnarayan, Paxton Turner
We introduce a new algorithm called {\sc Rec-Gen} for reconstructing the genealogy or \textit{pedigree} of an extant population purely from its genetic data.
no code implementations • 18 Dec 2020 • Elchanan Mossel
These lecture notes are based on lectures given in 2019 Saint-Flour Probability School.
Probability
no code implementations • 15 Jan 2021 • Ankur Moitra, Elchanan Mossel, Colin Sandon
These are Markov Random Fields where some of the nodes are censored (not observed).
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 • 15 Jun 2021 • Ankur Moitra, Elchanan Mossel, Colin Sandon
In this work, we study the computational complexity of determining whether a machine learning model that perfectly fits the training data will generalizes to unseen data.
no code implementations • 14 Sep 2021 • Frederic Koehler, Elchanan Mossel
In this work, we investigate the performance of low-degree polynomials for the reconstruction problem on trees.
no code implementations • 22 Mar 2022 • Souvik Dhara, Julia Gaudio, Elchanan Mossel, Colin Sandon
Spectral algorithms are an important building block in machine learning and graph algorithms.
1 code implementation • 10 Apr 2022 • Elchanan Mossel, David Vulakh
They showed that under these conditions if the average number of offspring is a sufficiently large constant, then it is possible to recover a large fraction of the pedigree structure and genetic content by an algorithm they named REC-GEN. We are interested in studying the performance of REC-GEN on simulated data generated according to the model.
no code implementations • 31 Jan 2023 • Elisabetta Cornacchia, Elchanan Mossel
Curriculum learning (CL) - training using samples that are generated and presented in a meaningful order - was introduced in the machine learning context around a decade ago.
no code implementations • 11 Sep 2023 • Anna Brandenberger, Cassandra Marcussen, Elchanan Mossel, Madhu Sudan
We study processes of societal knowledge accumulation, where the validity of a new unit of knowledge depends both on the correctness of its derivation and on the validity of the units it depends on.
no code implementations • 15 Nov 2023 • Jason Gaitonde, Elchanan Mossel
We show that a simple existing approach based on node-wise logistic regression provably succeeds at recovering the underlying model in several new settings where these assumptions are violated: (1) Given dynamically generated data from a wide variety of local Markov chains, like block or round-robin dynamics, logistic regression recovers the parameters with optimal sample complexity up to $\log\log n$ factors.
no code implementations • 14 Feb 2024 • Han Huang, Pakawut Jiradilok, Elchanan Mossel
Random geometric graphs are random graph models defined on metric spaces.
no code implementations • 22 Feb 2024 • Jason Gaitonde, Elchanan Mossel
Here, the $\mathbf{x}_{\ell}$ are assumed to be $\mathcal{N}(0, I_n)$ and the noise distribution $\mathbf{\eta}_{\ell}\sim \mathcal{D}$ is centered and independent of $\mathbf{x}_{\ell}$.