Search Results for author:
Found 21 papers, 5 papers with code
Tight Bounds for Influence in Diffusion Networks and Application to Bond Percolation and Epidemiology
In this paper, we derive theoretical bounds for the long-term influence of a node in an Independent Cascade Model (ICM).
Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks
Using this concept, we prove tight non-asymptotic bounds for the influence of a set of nodes, and we also provide an in-depth analysis of the critical time after which the contagion becomes super-critical.
Multivariate Hawkes Processes for Large-scale Inference
In this paper, we present a framework for fitting multivariate Hawkes processes for large-scale problems both in the number of events in the observed history $n$ and the number of event types $d$ (i. e. dimensions).
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.
A Spectral Method for Activity Shaping in Continuous-Time Information Cascades
Information Cascades Model captures dynamical properties of user activity in a social network.
KONG: Kernels for ordered-neighborhood graphs
We present novel graph kernels for graphs with node and edge labels that have ordered neighborhoods, i. e. when neighbor nodes follow an order.
Lipschitz regularity of deep neural networks: analysis and efficient estimation
First, we show that, even for two layer neural networks, the exact computation of this quantity is NP-hard and state-of-art methods may significantly overestimate it.
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
Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning
For smooth convex and non-convex objective functions, we provide matching lower and upper complexity bounds and show that a naive pipeline parallelization of Nesterov's accelerated gradient descent is optimal.
Coloring graph neural networks for node disambiguation
In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks(MPNNs).
Ego-based Entropy Measures for Structural Representations
Moreover, on graph classification tasks, we suggest the utilization of the generated structural embeddings for the transformation of an attributed graph structure into a set of augmented node attributes.
Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations
In the case of sub-Gaussian and centered noise, we prove that, with probability $1-\delta$, the number of iterations to reach a precision $\varepsilon$ for the squared gradient norm is $O(\varepsilon^{-2}\ln(1/\delta))$.
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration
This novel smoothing method is then used to improve first-order non-smooth optimization (both convex and non-convex) by allowing for a local exploration of the search space.
Ego-based Entropy Measures for Structural Representations on Graphs
Machine learning on graph-structured data has attracted high research interest due to the emergence of Graph Neural Networks (GNNs).
Improving Hierarchical Adversarial Robustness of Deep Neural Networks
Do all adversarial examples have the same consequences?
Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
To address this issue, we derive a theoretical analysis of the Lipschitz continuity of attention modules and introduce LipschitzNorm, a simple and parameter-free normalization for self-attention mechanisms that enforces the model to be Lipschitz continuous.
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): n \in \mathbb{N}^*\}$.
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure.
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.
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
On the contrary, we show, for convex, strongly convex and non-convex functions, that D-SGD can always recover generalization bounds analogous to those of classical SGD, suggesting that the choice of graph does not matter.
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.
