Search Results for author:
Found 35 papers, 14 papers with code
Automatic Rao-Blackwellization for Sequential Monte Carlo with Belief Propagation
Exact Bayesian inference on state-space models~(SSM) is in general untractable, and unfortunately, basic Sequential Monte Carlo~(SMC) methods do not yield correct approximations for complex models.
Interpretable Meta-Learning of Physical Systems
Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions.
FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
Model-based reinforcement learning is a powerful tool, but collecting data to fit an accurate model of the system can be costly.
Convergence beyond the over-parameterized regime using Rayleigh quotients
In this paper, we present a new strategy to prove the convergence of deep learning architectures to a zero training (or even testing) loss by gradient flow.
Online greedy identification of linear dynamical systems
This work addresses the problem of exploration in an unknown environment.
SiMCa: Sinkhorn Matrix Factorization with Capacity Constraints
In these applications, there is somewhat of an asymmetry between users and items: items are viewed as static points, their embeddings, capacities and locations constraining the allocation.
Correlation detection in trees for planted graph alignment
We then conjecture that graph alignment is not feasible in polynomial time when the associated tree detection problem is impossible.
Impossibility of Partial Recovery in the Graph Alignment Problem
Random graph alignment refers to recovering the underlying vertex correspondence between two random graphs with correlated edges.
Graph Pooling by Edge Cut
Compared to the case of images, it is not trivial to develop a pooling layer on graphs.
Graph Structural Aggregation for Explainable Learning
In order to use graph neural networks for graph classification, node embeddings must be aggregated to obtain a graph representation able to discriminate among different graphs (of possibly various sizes).
Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation.
Expressive Power of Invariant and Equivariant Graph Neural Networks
Various classes of Graph Neural Networks (GNN) have been proposed and shown to be successful in a wide range of applications with graph structured data.
Conditioned Query Generation for Task-Oriented Dialogue Systems
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation.
Invariant embedding for graph classification
The graph isomorphism problem tells us that fast representation of graphs is known if we require the representation to be both invariant to nodes permutation and able to discriminate two-isomorphic graphs.
Asymptotic Bayes risk for Gaussian mixture in a semi-supervised setting
In this paper, we compute analytically the gap between the best fully-supervised approach using only labeled data and the best semi-supervised approach using both labeled and unlabeled data.
Weighted Spectral Embedding of Graphs
We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance.
InfoCatVAE: Representation Learning with Categorical Variational Autoencoders
This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning.
Deep Representation for Patient Visits from Electronic Health Records
We show how to learn low-dimensional representations (embeddings) of patient visits from the corresponding electronic health record (EHR) where International Classification of Diseases (ICD) diagnosis codes are removed.
A Streaming Algorithm for Graph Clustering
We introduce a novel algorithm to perform graph clustering in the edge streaming setting.
Improving PageRank for Local Community Detection
Community detection is a classical problem in the field of graph mining.
Social and Information Networks Physics and Society
Non-Backtracking Spectrum of Degree-Corrected Stochastic Block Models
As a result, a clustering positively-correlated with the true communities can be obtained based on the second eigenvector of $B$ in the regime where $\mu_2^2 > \rho.$ In a previous work we obtained that detection is impossible when $\mu_2^2 < \rho,$ meaning that there occurs a phase-transition in the sparse regime of the Degree-Corrected Stochastic Block Model.
Fast Randomized Semi-Supervised Clustering
We consider the problem of clustering partially labeled data from a minimal number of randomly chosen pairwise comparisons between the items.
Clustering from Sparse Pairwise Measurements
We consider the problem of grouping items into clusters based on few random pairwise comparisons between the items.
Fast and Memory Optimal Low-Rank Matrix Approximation
This means that its average mean-square error converges to 0 as $m$ and $n$ grow large (i. e., $\|\hat{M}^{(k)}-M^{(k)} \|_F^2 = o(mn)$ with high probability, where $\hat{M}^{(k)}$ and $M^{(k)}$ denote the output of SLA and the optimal rank $k$ approximation of $M$, respectively).
An Impossibility Result for Reconstruction in a Degree-Corrected Planted-Partition Model
We consider the Degree-Corrected Stochastic Block Model (DC-SBM): a random graph on $n$ nodes, having i. i. d.
A spectral method for community detection in moderately-sparse degree-corrected stochastic block models
In particular, it does not need to know the number of communities.
A Spectral Algorithm with Additive Clustering for the Recovery of Overlapping Communities in Networks
This paper presents a novel spectral algorithm with additive clustering designed to identify overlapping communities in networks.
Streaming, Memory Limited Matrix Completion with Noise
We propose a streaming algorithm which produces an estimate of the original matrix with a vanishing mean square error, uses memory space scaling linearly with the ambient dimension of the matrix, i. e. the memory required to store the output alone, and spends computations as much as the number of non-zero entries of the input matrix.
Clustering and Inference From Pairwise Comparisons
We propose an efficient algorithm that accurately estimates the individual preferences for almost all users, if there are $r \max \{m, n\}\log m \log^2 n$ pairwise comparisons per type, which is near optimal in sample complexity when $r$ only grows logarithmically with $m$ or $n$.
Reconstruction in the Labeled Stochastic Block Model
The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types.
Combinatorial Bandits Revisited
In the adversarial setting under bandit feedback, we propose \textsc{CombEXP}, an algorithm with the same regret scaling as state-of-the-art algorithms, but with lower computational complexity for some combinatorial problems.
Spectral Detection in the Censored Block Model
We describe two spectral algorithms for this task based on the non-backtracking and the Bethe Hessian operators.
Streaming, Memory Limited Algorithms for Community Detection
The first algorithm is {\it offline}, as it needs to store and keep the assignments of nodes to clusters, and requires a memory that scales linearly with the network size.
Edge Label Inference in Generalized Stochastic Block Models: from Spectral Theory to Impossibility Results
The classical setting of community detection consists of networks exhibiting a clustered structure.
Spectrum Bandit Optimization
We consider the problem of allocating radio channels to links in a wireless network.
