output
20042025
most citedLeveraging Side Observations in Stochastic Bandits

67 citations

Showing 2021Show all

8 papers · 1 filter

math.OC2021★ 1 cited

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip

Mathieu Even, Raphaël Berthier, Francis Bach +5

We introduce the continuized Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continuou…

cs.CG2021★ 2 cited

Dots & Boxes is PSPACE-complete

Kevin Buchin, Mart Hagedoorn, Irina Kostitsyna +1

Exactly 20 years ago at MFCS, Demaine posed the open problem whether the game of Dots & Boxes is PSPACE-complete. Dots & Boxes has been studied extensively, with for instance a cha…

math.CV2021

On mappings of finite distortion that are quasiconformal in the unit disk

Olli Hirviniemi, Lauri Hitruhin, István Prause +1

We study quasiconformal mappings of the unit disk that have planar extension with controlled distortion. For these mappings we prove a bound for the modulus of continuity of the in…

cs.LG2021★ 28 cited

Input Similarity from the Neural Network Perspective

Guillaume Charpiat, Nicolas Girard, Loris Felardos +1

We first exhibit a multimodal image registration task, for which a neural network trained on a dataset with noisy labels reaches almost perfect accuracy, far beyond noise variance.…

cs.LG2021★ 4 cited

A simpler spectral approach for clustering in directed networks

Simon Coste, Ludovic Stephan

We study the task of clustering in directed networks. We show that using the eigenvalue/eigenvector decomposition of the adjacency matrix is simpler than all common methods which a…

cs.DC2021

Characterizing the Energy Trade-Offs of End-to-End Vehicular Communications using an Hyperfractal Urban Modelling

Dalia Popescu, Philippe Jacquet, Bernard Mans +1

We characterize trade-offs between the end-to-end communication delay and the energy in urban vehicular communications with infrastructure assistance. Our study exploits the self-s…