Search Results for author: Hemant Tyagi

Found 22 papers, 6 papers with code

Graph Matching via convex relaxation to the simplex

no code implementations31 Oct 2023 Ernesto Araya Valdivia, Hemant Tyagi

We use this condition to show exact one-step recovery of the ground truth (holding almost surely) via the mirror descent scheme, in the noiseless setting.

Graph Matching

Learning linear dynamical systems under convex constraints

no code implementations27 Mar 2023 Hemant Tyagi, Denis Efimov

We consider the problem of finite-time identification of linear dynamical systems from $T$ samples of a single trajectory.

Dynamic Ranking and Translation Synchronization

1 code implementation4 Jul 2022 Ernesto Araya, Eglantine Karlé, Hemant Tyagi

In this setup, we are given a sequence of comparison graphs $(G_t)_{t\in \mathcal{T}}$, where $\mathcal{T} \subset [0, 1]$ is a grid representing the time domain, and for each item $i$ and time $t\in \mathcal{T}$ there is an associated unknown strength parameter $z^*_{t, i}\in \mathbb{R}$.

Recommendation Systems Translation

Seeded graph matching for the correlated Wigner model via the projected power method

no code implementations8 Apr 2022 Ernesto Araya, Guillaume Braun, Hemant Tyagi

In the \emph{graph matching} problem we observe two graphs $G, H$ and the goal is to find an assignment (or matching) between their vertices such that some measure of edge agreement is maximized.

Graph Matching

An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guarantees

1 code implementation20 Dec 2021 Guillaume Braun, Hemant Tyagi, Christophe Biernacki

Our algorithm can be applied to general Contextual Stochastic Block Models and avoids hyperparameter tuning in contrast to previously proposed methods.

Clustering Stochastic Block Model

Recovering Hölder smooth functions from noisy modulo samples

1 code implementation2 Dec 2021 Michaël Fanuel, Hemant Tyagi

We consider a fixed design setting where the modulo samples are given on a regular grid.

Denoising

Dynamic Ranking with the BTL Model: A Nearest Neighbor based Rank Centrality Method

1 code implementation28 Sep 2021 Eglantine Karlé, Hemant Tyagi

When $(G_{t'})_{t' \in \mathcal{T}}$ is a sequence of Erd\"os-Renyi graphs, we provide non-asymptotic $\ell_2$ and $\ell_{\infty}$ error bounds for estimating $w_t^*$ which in particular establishes the consistency of this method in terms of $n$, and the grid size $\lvert\mathcal{T}\rvert$.

Recommendation Systems

Clustering multilayer graphs with missing nodes

no code implementations4 Mar 2021 Guillaume Braun, Hemant Tyagi, Christophe Biernacki

When these relationships have different modalities, they are better modelled by multilayer graphs where each layer is associated with one modality.

Clustering Stochastic Block Model

An extension of the angular synchronization problem to the heterogeneous setting

no code implementations29 Dec 2020 Mihai Cucuringu, Hemant Tyagi

This can be thought of as a natural extension of the angular synchronization problem to the heterogeneous setting of multiple groups of angles, where the measurement graph has an unknown edge-disjoint decomposition $G = G_1 \cup G_2 \ldots \cup G_k$, where the $G_i$'s denote the subgraphs of edges corresponding to each group.

Denoising modulo samples: k-NN regression and tightness of SDP relaxation

1 code implementation10 Sep 2020 Michaël Fanuel, Hemant Tyagi

The estimates of the samples $f(x_i)$ can be subsequently utilized to construct an estimate of the function $f$, with the aforementioned uniform error rate.

Denoising regression

Error analysis for denoising smooth modulo signals on a graph

no code implementations10 Sep 2020 Hemant Tyagi

The analysis is performed in a general setting where $G$ is any connected graph.

Denoising

Ranking and synchronization from pairwise measurements via SVD

no code implementations6 Jun 2019 Alexandre d'Aspremont, Mihai Cucuringu, Hemant Tyagi

Given a measurement graph $G= (V, E)$ and an unknown signal $r \in \mathbb{R}^n$, we investigate algorithms for recovering $r$ from pairwise measurements of the form $r_i - r_j$; $\{i, j\} \in E$.

SPONGE: A generalized eigenproblem for clustering signed networks

1 code implementation18 Apr 2019 Mihai Cucuringu, Peter Davies, Aldo Glielmo, Hemant Tyagi

We introduce a principled and theoretically sound spectral method for $k$-way clustering in signed graphs, where the affinity measure between nodes takes either positive or negative values.

Constrained Clustering Stochastic Block Model

Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping

no code implementations9 Mar 2018 Mihai Cucuringu, Hemant Tyagi

Given the samples $(x_i, y_i)_{i=1}^{n}$, our goal is to recover smooth, robust estimates of the clean samples $f(x_i) \bmod 1$.

Denoising Riemannian optimization

On denoising modulo 1 samples of a function

no code implementations27 Oct 2017 Mihai Cucuringu, Hemant Tyagi

Given the samples $(x_i, y_i)_{i=1}^{n}$ our goal is to recover smooth, robust estimates of the clean samples $f(x_i) \bmod 1$.

Denoising

Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions

no code implementations2 May 2016 Hemant Tyagi, Anastasios Kyrillidis, Bernd Gärtner, Andreas Krause

A function $f: \mathbb{R}^d \rightarrow \mathbb{R}$ is a Sparse Additive Model (SPAM), if it is of the form $f(\mathbf{x}) = \sum_{l \in \mathcal{S}}\phi_{l}(x_l)$ where $\mathcal{S} \subset [d]$, $|\mathcal{S}| \ll d$.

Additive models Vocal Bursts Intensity Prediction

Learning Sparse Additive Models with Interactions in High Dimensions

no code implementations18 Apr 2016 Hemant Tyagi, Anastasios Kyrillidis, Bernd Gärtner, Andreas Krause

For some $\mathcal{S}_1 \subset [d], \mathcal{S}_2 \subset {[d] \choose 2}$, the function $f$ is assumed to be of the form: $$f(\mathbf{x}) = \sum_{p \in \mathcal{S}_1}\phi_{p} (x_p) + \sum_{(l, l^{\prime}) \in \mathcal{S}_2}\phi_{(l, l^{\prime})} (x_{l}, x_{l^{\prime}}).$$ Assuming $\phi_{p},\phi_{(l, l^{\prime})}$, $\mathcal{S}_1$ and, $\mathcal{S}_2$ to be unknown, we provide a randomized algorithm that queries $f$ and exactly recovers $\mathcal{S}_1,\mathcal{S}_2$.

Additive models Vocal Bursts Intensity Prediction

Efficient Sampling for Learning Sparse Additive Models in High Dimensions

no code implementations NeurIPS 2014 Hemant Tyagi, Bernd Gärtner, Andreas Krause

We consider the problem of learning sparse additive models, i. e., functions of the form: $f(\vecx) = \sum_{l \in S} \phi_{l}(x_l)$, $\vecx \in \matR^d$ from point queries of $f$.

Additive models Compressive Sensing +1

Stochastic continuum armed bandit problem of few linear parameters in high dimensions

no code implementations1 Dec 2013 Hemant Tyagi, Sebastian Stich, Bernd Gärtner

We consider a stochastic continuum armed bandit problem where the arms are indexed by the $\ell_2$ ball $B_{d}(1+\nu)$ of radius $1+\nu$ in $\mathbb{R}^d$.

Learning Non-Parametric Basis Independent Models from Point Queries via Low-Rank Methods

no code implementations7 Oct 2013 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 twice continuously differentiable almost everywhere, and A \in R^{k \times d} is a rank k matrix, where k << d. We propose a randomized, polynomial-complexity sampling scheme for estimating such functions.

Continuum armed bandit problem of few variables in high dimensions

no code implementations21 Apr 2013 Hemant Tyagi, Bernd Gärtner

We consider the stochastic and adversarial settings of continuum armed bandits where the arms are indexed by [0, 1]^d.

Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.