4 citations · 8 across the 8 of their papers we have counts for
10 papers
Polylogarithmic Collective Tree Exploration
Romain Cosson, Laurent Massoulié
We study asynchronous collective tree exploration, where agents with unrestricted communication start at the root of an unknown tree and discover edges online. At each step, an…
Asynchronous Collective Tree Exploration: a Distributed Algorithm, and a new Lower Bound
Romain Cosson, Laurent Massoulié
We study the problem of collective tree exploration in which a team of mobile agents must collectively visit all nodes of an unknown tree in as few moves as possible. The agent…
Collective Tree Exploration via Potential Function Method
Romain Cosson, Laurent Massoulié
We study the problem of collective tree exploration (CTE) where a team of agents is tasked to traverse all the edges of an unknown tree as fast as possible, assuming complete c…
Breaking the k/log k Barrier in Collective Tree Exploration via Tree-Mining
Romain Cosson
In collective tree exploration, a team of mobile agents is tasked to go through all edges of an unknown tree as fast as possible. An edge of the tree is revealed to the team wh…
Breadth-First Depth-Next: Optimal Collaborative Exploration of Trees with Low Diameter
Romain Cosson, Laurent Massoulié, Laurent Viennot
We consider the problem of collaborative tree exploration posed by Fraigniaud, Gasieniec, Kowalski, and Pelc where a team of agents is tasked to collectively go through all the…
Gradient Descent for Low-Rank Functions
Romain Cosson, Ali Jadbabaie, Anuran Makur +2
Several recent empirical studies demonstrate that important machine learning tasks, e.g., training deep neural networks, exhibit low-rank structure, where the loss function varies…
Universal Online Learning with Unbounded Losses: Memory Is All You Need
Moise Blanchard, Romain Cosson, Steve Hanneke
We resolve an open problem of Hanneke on the subject of universally consistent online learning with non-i.i.d. processes and unbounded losses. The notion of an optimistically unive…
Universal Online Learning with Bounded Loss: Reduction to Binary Classification
Moïse Blanchard, Romain Cosson
We study universal consistency of non-i.i.d. processes in the context of online learning. A stochastic process is said to admit universal consistency if there exists a learner that…
Quantifying Variational Approximation for the Log-Partition Function
Romain Cosson, Devavrat Shah
Variational approximation, such as mean-field (MF) and tree-reweighted (TRW), provide a computationally efficient approximation of the log-partition function for a generic graphica…
Synthetic Interventions
Anish Agarwal, Devavrat Shah, Dennis Shen
The synthetic controls (SC) methodology is a prominent tool for policy evaluation in panel data applications. Researchers commonly justify the SC framework with a low-rank matrix f…