The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed
Bandit with Many Arms
February 24, 2020
| | |
Computer Science
Statistics
Machine Learning
Machine Learning
We investigate a Bayesian k-armed bandit problem in the \emph{many-armed}
regime, where k≥T and T represents the time horizon. Initially,
and aligned with recent literature on many-armed bandit problems, we observe
that su...
Quantized Decentralized Stochastic Learning over Directed Graphs
February 23, 2020
| | | | | | |
Computer Science
Electrical Engineering and Systems Science
Distributed, Parallel, and Cluster Computing
Machine Learning
Multiagent Systems
Systems and Control
Signal Processing
Systems and Control
Distributed, Parallel, and Cluster Computing
Machine Learning
Multiagent Systems
Systems and Control
Signal Processing
Systems and Control
We consider a decentralized stochastic learning problem where data points are
distributed among computing nodes communicating over a directed graph. As the
model size gets large, decentralized learning faces a major bottleneck that is
the h...
A computer-friendly construction of the monster
February 22, 2020
Mathematics
Group Theory
Let M be the monster group which is the largest sporadic finite
simple group, and has first been constructed in 1982 by Griess. In 1985, Conway
has constructed a 196884-dimensional representation ρ of M with
matri...
Extracting and Validating Explanatory Word Archipelagoes using Dual
Entropy
February 21, 2020
Computer Science
Computation and Language
The logical connectivity of text is represented by the connectivity of words
that form archipelagoes. Here, each archipelago is a sequence of islands of the
occurrences of a certain word. An island here means the local sequence of
sentences...
Hyperinvariant subspaces for normaloid essential isometric operators
February 21, 2020
|
Mathematics
Functional Analysis
In this article, we prove the existence of a non-trivial hyperinvariant
subspace for a subclass of compact perturbations of scalar multiple of a
partial isometry. Later, we illustrate that this class contains several
important classes of op...
Misspecification-robust likelihood-free inference in high dimensions
February 21, 2020
| | | | |
Statistics
Computation
Methodology
Machine Learning
Likelihood-free inference for simulator-based statistical models has
developed rapidly from its infancy to a useful tool for practitioners. However,
models with more than a handful of parameters still generally remain a
challenge for the Ap...
Realization of manifolds as leaves using graph colorings
February 20, 2020
| | |
Mathematics
Geometric Topology
Dynamical Systems
Geometric Topology
Dynamical Systems
It is proved that any (repetitive) Riemannian manifold of bounded geometry
can be realized as a leaf of some (minimal) Riemannian matchbox manifold
without holonomy. Our methods can be adapted to achieve Cantor transversals or
a prescribed ...
A mean-field model of Integrate-and-Fire neurons: non-linear stability
of the stationary solutions
February 20, 2020
Mathematics
Probability
Analysis of PDEs
We investigate a stochastic network composed of Integrate-and-Fire spiking
neurons, focusing on its mean-field asymptotics. We consider an invariant
probability measure of the McKean-Vlasov equation and establish an explicit
sufficient cond...
Evolution of Cosmological Total Energy Density and Transient Periods in
Cosmology
February 20, 2020
Physics
General Relativity and Quantum Cosmology
High Energy Physics - Phenomenology
The evolution of the Universe is traditionally examined by monitoring how its
material content evolves as it expands. This model of an isolated system is
expressed as the equation of motion of the bulk but segmented into different
epochs. I...
Adaptive Graph Auto-Encoder for General Data Clustering
February 20, 2020
| |
Computer Science
Statistics
Machine Learning
Machine Learning
Graph-based clustering plays an important role in the clustering area. Recent
studies about graph convolution neural networks have achieved impressive
success on graph type data. However, in general clustering tasks, the graph
structure of ...