Arthur D Szlam, Mauro Maggioni, Ronald R Coifman
on graphs with function-adapted diffusion processes
Michael W. Mahoney, Mauro Maggioni, Petros Drineas
Abstract. Motivated by numerous applications in which the data may be modeled by a variable subscripted by three or more indices, we develop a tensor-based extension of the matrix CUR decomposition....
REMARKS ON THE BOX PROBLEM. (2009)
Nets Hawk Katz, Elliot Krop, Mauro Maggioni
In [CCW], in connection with estimates on Fourier integral operators, the following question was raised. Let Q =[0, 1] n ⊂ R n,
Arthur D Szlam, Mauro Maggioni, Ronald R Coifman
on graphs with function-adapted diffusion processes
Abstract Diffusion Wavelets (2008)
Ronald R. Coifman, Mauro Maggioni
We present a multiresolution construction for efficiently computing, compressing and applying large powers of operators that have high powers with low numerical rank. This allows the fast computation...
Abstract Diffusion Wavelet Packets (2008)
James C Bremer, Ronald R Coifman, Mauro Maggioni, Arthur D Szlam
Diffusion wavelets can be constructed on manifolds, graphs and allow an efficient multiscale representation of powers of a diffusion operator acting on their domain. While diffusion wavelets are...
Sridhar Mahadevan, Mauro Maggioni
We investigate the problem of automatically constructing efficient representations or basis functions for approximating value functions based on analyzing the structure and topology of the state...
Wavelet frames on groups and hypergroups via discretization of calderón formulas (2008)
Abstract. Continuous wavelets are often studied in the general framework of representation theory of square-integrable representations, or by using convolution relations and Fourier transforms. We...
Qiang Wu, Justin Guinney, Mauro Maggioni, Sayan Mukherjee
This paper develops and discusses a modeling framework called learning gradients that allows for predictive models that simultaneously infer the geometry and statistical dependencies of the input...
Arthur D Szlam, Mauro Maggioni, Ronald R Coifman
on graphs with function-adapted diffusion processes
Sridhar Mahadevan, Mauro Maggioni
We investigate the problem of automatically constructing efficient representations or basis functions for approximating value functions based on analyzing the structure and topology of the state...
Qiang Wu, Justin Guinney, Mauro Maggioni, Sayan Mukherjee
This paper develops and discusses a modeling framework called learning gradients that allows for predictive models that simultaneously infer the geometry and statistical dependencies of the input...
Sridhar Mahadevan, Mauro Maggioni
We investigate the problem of automatically constructing efficient representations or basis functions for approximating value functions based on analyzing the structure and topology of the state...
Universal local parametrizations via heat kernels and eigenfunctions of the Laplacian (2007)
Jones, Peter W., Maggioni, Mauro, Schul, Raanan
We use heat kernels or eigenfunctions of the Laplacian to construct local coordinates on large classes of Euclidean domains and Riemannian manifolds (not necessarily smooth, e.g. with...
Sridhar Mahadevan, Mauro Maggioni, Carlos Guestrin
This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described...
Sridhar Mahadevan, Mauro Maggioni, Carlos Guestrin
This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described...
Abstract Non-Stationary Analysis on Datasets and Applications (2006)
Dissertation Directors, Ronald Coifman, Mauro Maggioni, Arthur Szlam, Masood Aryapoor, Jim Bremer, ...
In the first part of this thesis, we study the use of anisotropic diffusions on datasets as a tool for signal processing and machine learning. We modify the geometry of the data by adding feature...
Mauro Maggioni, Sridhar Mahadevan, Sridhar Mahadevan
We present a novel hierarchical framework for solving Markov decision processes (MDPs) using a multiscale method called diffusion wavelets. Diffusion wavelet bases significantly differ from the...
Sridhar Mahadevan, Mauro Maggioni
This paper introduces a novel paradigm for solving Markov decision processes (MDPs), based on jointly learning representations and optimal policies. Proto-value functions are geometrically customized...
Sridhar Mahadevan, Mauro Maggioni, Carlos Guestrin
This paper introduces a novel spectral framework for solving Markov decision processes (MDPs) by jointly learning representations and optimal policies. The major components of the framework described...
Ronald R. Coifman, Mauro Maggioni
Our goal in this paper is to show that many of the tools of signal processing, adapted Fourier and wavelet analysis can be naturally lifted to the setting of digital data clouds, graphs and...
Regularization on graphs with function-adapted diffusion process (2006)
Arthur D. Szlam, Mauro Maggioni, Ronald R. Coifman, Zoubin Ghahrmani
Harmonic analysis and diffusion on discrete data has been shown to lead to state-of-the-art algorithms for machine learning tasks, especially in the context of semi-supervised and transductive...
Mauro Maggioni, James C. Bremer, Ronald R. Coifman, Arthur D. Szlam
Recent work by some of the authors presented a novel construction of a multiresolution analysis on manifolds and graphs, acted upon by a given symmetric Markov semigroup {T t}t≥0, for which T t has...
Arthur D Szlam, Mauro Maggioni, Ronald R Coifman, James C Bremer
Classically, analysis on manifolds and graphs has been based on the study of the eigenfunctions of the Laplacian and its generalizations. These objects from differential geometry and analysis on...
Mauro Maggioni, Sridhar Mahadevan
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S | 3) to directly solve the Bellman system of |S | linear equations...
Fast direct policy evaluation using multiscale analysis of markov diffusion processes (2005)
Mauro Maggioni, Sridhar Mahadevan
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S | 3) to directly solve the Bellman system of |S | linear equations...
Fast direct policy evaluation using multiscale analysis of markov diffusion processes (2005)
Mauro Maggioni, Sridhar Mahadevan
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S | 3) to directly solve the Bellman system of |S | linear equations...
Sridhar Mahadevan, Mauro Maggioni
We investigate the problem of automatically constructing efficient representations or basis functions for approximating value functions based on analyzing the structure and topology of the state...
Multiresolution analysis associated to diffusion semigroups: construction and fast algorithms (2004)
Ronald R. Coifman, Mauro Maggioni
Abstract. We introduce a novel multiresolution construction for efficiently computing, compressing and applying large powers of operators that have high powers with low numerical rank. This allows...
Auditory Display of Hyperspectral Colon Tissue Images using Vocal Synthesis Models (2004)
Ryan J. Cassidy, Jonathan Berger, Kyogu Lee, Mauro Maggioni, Ronald R. Coifman
The human ability to recognize, identify and compare sounds based on their approximation of particular vowels provides an intuitive, easily learned representation for complex data. We describe...
Discretization of continueous wavelet transforms and wavelet frames / (2002)
Thesis (Ph. D.)--Washington University, 2002. Dept. of Mathematics.
Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels
Jones, Peter W., Maggioni, Mauro, Schul, Raanan
We use heat kernels or eigenfunctions of the Laplacian to construct local coordinates on large classes of Euclidean domains and Riemannian manifolds (not necessarily smooth, e.g., with 𝒞α...