Search Results for author:
Found 23 papers, 4 papers with code
Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization
Decentralized and asynchronous communications are two popular techniques to speedup communication complexity of distributed machine learning, by respectively removing the dependency over a central orchestrator and the need for synchronization.
Generalization Error of First-Order Methods for Statistical Learning with Generic Oracles
In this paper, we provide a novel framework for the analysis of generalization error of first-order optimization algorithms for statistical learning when the gradient can only be accessed through partial observations given by an oracle.
Statistical limits of correlation detection in trees
In this paper we address the problem of testing whether two observed trees $(t, t')$ are sampled either independently or from a joint distribution under which they are correlated.
Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
In this work, we introduce pairwise network differential privacy, a relaxation of LDP that captures the fact that the privacy leakage from a node $u$ to a node $v$ may depend on their relative position in the graph.
Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms
We introduce the ``continuized'' Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter.
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.
A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip
We introduce the continuized Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter.
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.
Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
Dimension is an inherent bottleneck to some modern learning tasks, where optimization methods suffer from the size of the data.
Partial Recovery in the Graph Alignment Problem
Our focus here is on partial recovery, i. e., we look for a one-to-one mapping which is correct on a fraction of the nodes of the graph rather than on all of them, and we assume that the two input graphs to the problem are correlated Erd\H{o}s-R\'enyi graphs of parameters $(n, q, s)$.
Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite Sums
In this work, we study the problem of minimizing the sum of strongly convex functions split over a network of $n$ nodes.
Optimization and Control Distributed, Parallel, and Cluster Computing
Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives
Applying $ESDACD$ to quadratic local functions leads to an accelerated randomized gossip algorithm of rate $O( \sqrt{\theta_{\rm gossip}/n})$ where $\theta_{\rm gossip}$ is the rate of the standard randomized gossip.
Efficient inference in stochastic block models with vertex labels
Whenever this function has multiple fixed points, the belief propagation algorithm may not perform optimally.
Optimal Algorithms for Non-Smooth Distributed Optimization in Networks
Under the global regularity assumption, we provide a simple yet efficient algorithm called distributed randomized smoothing (DRS) based on a local smoothing of the objective function, and show that DRS is within a $d^{1/4}$ multiplicative factor of the optimal convergence rate, where $d$ is the underlying dimension.
Optimization and Control
Optimal algorithms for smooth and strongly convex distributed optimization in networks
For centralized (i. e. master/slave) algorithms, we show that distributing Nesterov's accelerated gradient descent is optimal and achieves a precision $\varepsilon > 0$ in time $O(\sqrt{\kappa_g}(1+\Delta\tau)\ln(1/\varepsilon))$, where $\kappa_g$ is the condition number of the (global) function to optimize, $\Delta$ is the diameter of the network, and $\tau$ (resp.
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.
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.
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.
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.
The Price of Privacy in Untrusted Recommendation Engines
In the information-rich regime, where each user rates at least a constant fraction of items, a spectral clustering approach is shown to achieve a sample-complexity lower bound derived from a simple information-theoretic argument based on Fano's inequality.
Distributed User Profiling via Spectral Methods
We prove that without prior knowledge of the compositions of the classes, based solely on few random observed ratings (namely $O(N\log N)$ such ratings for $N$ users), we can predict user preference with high probability for unrated items by running a local vote among users with similar profile vectors.
