4.8k citations · 5.1k across the 59 of their papers we have counts for
9 papers · 1 filter
Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme
K. E. Avrachenkov, V. S. Borkar, H. P. Dolhare +1
We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theo…
LFGCN: Levitating over Graphs with Levy Flights
Yuzhou Chen, Yulia R. Gel, Konstantin Avrachenkov
Due to high utility in many applications, from social networks to blockchain to power grids, deep learning on non-Euclidean objects such as graphs and manifolds, coined Geometric D…
Higher-Order Spectral Clustering for Geometric Graphs
Konstantin Avrachenkov, Andrei Bobu, Maximilien Dreveton
The present paper is devoted to clustering geometric graphs. While the standard spectral clustering is often not effective for geometric graphs, we present an effective generalizat…
Almost exact recovery in noisy semi-supervised learning
Konstantin Avrachenkov, Maximilien Dreveton
Graph-based semi-supervised learning methods combine the graph structure and labeled data to classify unlabeled data. In this work, we study the effect of a noisy oracle on classif…
Whittle index based Q-learning for restless bandits with average reward
Konstantin E. Avrachenkov, Vivek S. Borkar
A novel reinforcement learning algorithm is introduced for multiarmed restless bandits with average reward, using the paradigms of Q-learning and Whittle index. Specifically, we le…
Graphlet Count Estimation via Convolutional Neural Networks
Xutong Liu, Yu-Zhen Janice Chen, John C. S. Lui +1
Graphlets are defined as k-node connected induced subgraph patterns. For an undirected graph, 3-node graphlets include close triangle and open triangle. When k = 4, there are six t…
The Power of Side-information in Subgraph Detection
Arun Kadavankandy, Konstantin Avrachenkov, Laura Cottatellucci +1
In this work, we tackle the problem of hidden community detection. We consider Belief Propagation (BP) applied to the problem of detecting a hidden Erdős-Rényi (ER) graph embedded…
Parallel and Distributed Approaches for Graph Based Semi-supervised Learning
Konstantin Avrachenkov, Vivek Borkar, Krishnakant Saboo
Two approaches for graph based semi-supervised learning are proposed. The firstapproach is based on iteration of an affine map. A key element of the affine map iteration is sparsem…
Semi-supervised Learning with Regularized Laplacian
Konstantin Avrachenkov, Pavel Chebotarev, Alexey Mishenin
We study a semi-supervised learning method based on the similarity graph and RegularizedLaplacian. We give convenient optimization formulation of the Regularized Laplacian method a…