72 citations · 157 across the 23 of their papers we have counts for
25 papers
Learning linear dynamical systems under convex constraints
Hemant Tyagi, Denis Efimov
We consider the problem of finite-time identification of linear dynamical systems from samples of a single trajectory. Recent results have predominantly focused on the setup wh…
Dynamic Ranking and Translation Synchronization
Ernesto Araya, Eglantine Karlé, Hemant Tyagi
In many applications, such as sport tournaments or recommendation systems, we have at our disposal data consisting of pairwise comparisons between a set of items (or players).…
Minimax Optimal Clustering of Bipartite Graphs with a Generalized Power Method
Guillaume Braun, Hemant Tyagi
Clustering bipartite graphs is a fundamental task in network analysis. In the high-dimensional regime where the number of rows and the number of columns of the associat…
Seeded graph matching for the correlated Gaussian Wigner model via the projected power method
Ernesto Araya, Guillaume Braun, Hemant Tyagi
In the \emph{graph matching} problem we observe two graphs and the goal is to find an assignment (or matching) between their vertices such that some measure of edge agreement…
Recovering Hölder smooth functions from noisy modulo samples
Michaël Fanuel, Hemant Tyagi
In signal processing, several applications involve the recovery of a function given noisy modulo samples. The setting considered in this paper is that the samples corrupted by an a…
An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees
Guillaume Braun, Hemant Tyagi, Christophe Biernacki
Real-world networks often come with side information that can help to improve the performance of network analysis tasks such as clustering. Despite a large number of empirical and…
Dynamic Ranking with the BTL Model: A Nearest Neighbor based Rank Centrality Method
Eglantine Karlé, Hemant Tyagi
Many applications such as recommendation systems or sports tournaments involve pairwise comparisons within a collection of items, the goal being to aggregate the binary outcome…
Clustering multilayer graphs with missing nodes
Guillaume Braun, Hemant Tyagi, Christophe Biernacki
Relationship between agents can be conveniently represented by graphs. When these relationships have different modalities, they are better modelled by multilayer graphs where each…
An extension of the angular synchronization problem to the heterogeneous setting
Mihai Cucuringu, Hemant Tyagi
Given an undirected measurement graph , the classical angular synchronization problem consists of recovering unknown angles from a collection of noisy…
Regularized spectral methods for clustering signed networks
Mihai Cucuringu, Apoorv Vikram Singh, Déborah Sulem +1
We study the problem of -way clustering in signed graphs. Considerable attention in recent years has been devoted to analyzing and modeling signed graphs, where the affinity mea…
Error analysis for denoising smooth modulo signals on a graph
Hemant Tyagi
In many applications, we are given access to noisy modulo samples of a smooth function with the goal being to robustly unwrap the samples, i.e., to estimate the original samples of…
Denoising modulo samples: k-NN regression and tightness of SDP relaxation
Michaël Fanuel, Hemant Tyagi
Many modern applications involve the acquisition of noisy modulo samples of a function , with the goal being to recover estimates of the original samples of . For a Lipschitz…
Ranking and synchronization from pairwise measurements via SVD
Alexandre d'Aspremont, Mihai Cucuringu, Hemant Tyagi
Given a measurement graph and an unknown signal , we investigate algorithms for recovering from pairwise measurements of the form ; $\…
SPONGE: A generalized eigenproblem for clustering signed networks
Mihai Cucuringu, Peter Davies, Aldo Glielmo +1
We introduce a principled and theoretically sound spectral method for -way clustering in signed graphs, where the affinity measure between nodes takes either positive or negativ…
Multi-kernel unmixing and super-resolution using the Modified Matrix Pencil method
Stéphane Chrétien, Hemant Tyagi
Consider groups of point sources or spike trains, with the group represented by . For a function , let $g_l(t) = g(…
Sparse non-negative super-resolution -- simplified and stabilised
Armin Eftekhari, Jared Tanner, Andrew Thompson +2
The convolution of a discrete measure, , with a local window function, , is a common model for a measurement device whose resolution is substantia…
Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping
Mihai Cucuringu, Hemant Tyagi
Consider an unknown smooth function , and say we are given noisy mod 1 samples of , i.e., , for $x_i \in [0,1]…
Learning general sparse additive models from point queries in high dimensions
Hemant Tyagi, Jan Vybiral
We consider the problem of learning a -variate function defined on the cube , where the algorithm is assumed to have black box access to sampl…
On denoising modulo 1 samples of a function
Mihai Cucuringu, Hemant Tyagi
Consider an unknown smooth function , and say we are given noisy samples of , i.e., for …
Formal Verification of Obstacle Avoidance and Navigation of Ground Robots
Stefan Mitsch, Khalil Ghorbal, David Vogelbacher +1
The safety of mobile robots in dynamic environments is predicated on making sure that they do not collide with obstacles. In support of such safety arguments, we analyze and formal…
Learning Sparse Additive Models with Interactions in High Dimensions
Hemant Tyagi, Anastasios Kyrillidis, Bernd Gärtner +1
A function is referred to as a Sparse Additive Model (SPAM), if it is of the form , whe…
Stochastic continuum armed bandit problem of few linear parameters in high dimensions
Hemant Tyagi, Sebastian Stich, Bernd Gärtner
We consider a stochastic continuum armed bandit problem where the arms are indexed by the ball of radius in . The reward functions $r :B_{…
Learning Non-Parametric Basis Independent Models from Point Queries via Low-Rank Methods
Hemant Tyagi, Volkan Cevher
We consider the problem of learning multi-ridge functions of the form f(x) = g(Ax) from point evaluations of f. We assume that the function f is defined on an l_2-ball in R^d, g is…
Continuum armed bandit problem of few variables in high dimensions
Hemant Tyagi, Bernd Gärtner
We consider the stochastic and adversarial settings of continuum armed bandits where the arms are indexed by [0,1]^d. The reward functions r:[0,1]^d -> R are assumed to intrinsical…