Personne
Stefan Vlaski
Cette personne n’est plus à l’EPFL
Publications associées (40)
Social Learning with Disparate Hypotheses
Ali H. Sayed, Stefan Vlaski, Virginia Bordignon, Konstantinos Ntemos
In this paper we study the problem of social learning under multiple true hypotheses and self-interested agents. In this setup, each agent receives data that might be generated from a different hypothesis (or state) than the data other agents receive. In c ...
IEEE2022Finite Bit Quantization For Decentralized Learning Under Subspace Constraints
Ali H. Sayed, Stefan Vlaski, Roula Nassif, Marco Carpentiero
In this paper, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers across the network to lie in low-dimensional subspaces. This constrained form ...
IEEE2022Gramian-Based Adaptive Combination Policies For Diffusion Learning Over Networks
Ali H. Sayed, Stefan Vlaski, Yigit Efe Erginbas
This paper presents an adaptive combination strategy for distributed learning over diffusion networks. Since learning relies on the collaborative processing of the stochastic information at the dispersed agents, the overall performance can be improved by d ...
IEEE2021Distributed Learning in Non-Convex Environments-Part II: Polynomial Escape From Saddle-Points
The diffusion strategy for distributed learning from streaming data employs local stochastic gradient updates along with exchange of iterates over neighborhoods. In Part I [3] of this work we established that agents cluster around a network centroid and pr ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021Distributed Learning in Non-Convex Environments-Part I: Agreement at a Linear Rate
Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments. Most available wor ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021Social Learning Under Inferential Attacks
Ali H. Sayed, Stefan Vlaski, Virginia Bordignon, Konstantinos Ntemos
A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at driving the network beliefs to the wrong hypothesis. The adversaries a ...
IEEE2021Graph-Homomorphic Perturbations For Private Decentralized Learning
Decentralized algorithms for stochastic optimization and learning rely on the diffusion of information through repeated local exchanges of intermediate estimates. Such structures are particularly appealing in situations where agents may be hesitant to shar ...
IEEE2021Network Classifiers Based On Social Learning
Ali H. Sayed, Stefan Vlaski, Virginia Bordignon
This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to ...
IEEE2021Distributed Meta-Learning with Networked Agents
Ali H. Sayed, Mert Kayaalp, Stefan Vlaski
Meta-learning aims to improve efficiency of learning new tasks by exploiting the inductive biases obtained from related tasks. Previous works consider centralized or federated architectures that rely on central processors, whereas, in this paper, we propos ...
EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP2021Competing Adaptive Networks
Adaptive networks have the capability to pursue solutions of global stochastic optimization problems by relying only local interactions within neighborhoods. The diffusion of information through repeated interactions allows for globally optimal behavior, w ...
IEEE2021