12 citations · 23 across the 13 of their papers we have counts for
15 papers
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
Anik Kumar Paul, Nibedita Roy, Nagesh Talagani +3
We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achie…
Game-Theoretic Analysis of Transaction Selection in DAG-Based Distributed Ledgers
Sebastian Müller, Alexandre Reiffers-Masson
Transaction selection in parallel or DAG-based distributed ledger technologies (DLTs) is a crucial challenge that directly impacts throughput, fairness, and validator incentives. I…
Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery
Vishal Halder, Alexandre Reiffers-Masson, Abdeldjalil Aïssa-El-Bey +1
Recovery from linear measurements under sparse adversarial corruption is typically formulated as an exact-recovery problem: one seeks structural conditions on (e.g., r…
Online Learning of Weakly Coupled MDP Policies for Load Balancing and Auto Scaling
S. R. Eshwar, Lucas Lopes Felipe, Alexandre Reiffers-Masson +2
Load balancing and auto scaling are at the core of scalable, contemporary systems, addressing dynamic resource allocation and service rate adjustments in response to workload chang…
Certainty Equivalence Control-Based Heuristics in Multi-Stage Convex Stochastic Optimization Problems
Chen Yan, Alexandre Reiffers-Masson
We examine a multi-stage stochastic optimization problem characterized by stagewise-independent, decision-dependent noises with strict constraints. The problem assumes convexity in…
An Interactive Interface for Novel Class Discovery in Tabular Data
Colin Troisemaine, Joachim Flocon-Cholet, Stéphane Gosselin +3
Novel Class Discovery (NCD) is the problem of trying to discover novel classes in an unlabeled set, given a labeled set of different but related classes. The majority of NCD method…
Online Learning with Adversaries: A Differential-Inclusion Analysis
Swetha Ganesh, Alexandre Reiffers-Masson, Gugan Thoppe
We introduce an observation-matrix-based framework for fully asynchronous online Federated Learning (FL) with adversaries. In this work, we demonstrate its effectiveness in estimat…
Novel Class Discovery: an Introduction and Key Concepts
Colin Troisemaine, Vincent Lemaire, Stéphane Gosselin +3
Novel Class Discovery (NCD) is a growing field where we are given during training a labeled set of known classes and an unlabeled set of different classes that must be discovered.…
Stability of local tip pool sizes
Sebastian Müller, Isabel Amigo, Alexandre Reiffers-Masson +1
In directed acyclic graph (DAG)-based distributed ledgers, unreferenced blocks (tips) form the backlog of a distributed queueing system. Each new block creates one tip and attempts…
Geometry-preserving Lie Group Integrators For Differential Equations On The Manifold Of Symmetric Positive Definite Matrices
Lucas Drumetz, Alexandre Reiffers-Masson, Naoufal El Bekri +1
In many applications, one encounters signals that lie on manifolds rather than a Euclidean space. In particular, covariance matrices are examples of ubiquitous mathematical objects…
Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation
Alexandre Reiffers-Masson, Isabel Amigo
In this paper, we propose an iterative scheme for distributed Byzantineresilient estimation of a gradient associated with a black-box model. Our algorithm is based on simultaneous…
A Method for Discovering Novel Classes in Tabular Data
Colin Troisemaine, Joachim Flocon-Cholet, Stéphane Gosselin +3
In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes. While NCD has recently gained attention from…
Opinion shaping in social networks using reinforcement learning
Vivek Borkar, Alexandre Reiffers-Masson
In this paper, we study how to shape opinions in social networks when the matrix of interactions is unknown. We consider classical opinion dynamics with some stubborn agents and th…
Reputation-Based Information Design for Inducing Prosocial Behavior
Alexandre Reiffers-Masson, Rajesh Sundaresan
We study the idea of information design for inducing prosocial behavior in the context of electricity consumption. We consider a continuum of agents. Each agent has a different int…
Opinion-Based Centrality in Multiplex Networks: A Convex Optimization Approach
Alexandre Reiffers-Masson, Vincent Labatut
Most people simultaneously belong to several distinct social networks, in which their relations can be different. They have opinions about certain topics, which they share and spre…