Publication

Online performance guarantees for sparse recovery

Related publications (31)

Discovery of Slow Variables in a Class Of Multiscale Stochastic Systems Via Neural Networks

Jan Sickmann Hesthaven, Przemyslaw Zielinski

Finding a reduction of complex, high-dimensional dynamics to its essential, low-dimensional "heart" remains a challenging yet necessary prerequisite for designing efficient numerical approaches. Machine learning methods have the potential to provide a gene ...

2022

Efficient Learning of a Linear Dynamical System with Stability Guarantees

Daniel Kuhn, Tobias Sutter, Wouter Jongeneel

We propose a principled method for projecting an arbitrary square matrix to the non- convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an information-theoretic sense and ...

2023

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Daniel Kuhn, Tobias Sutter, Andreas Krause

Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribut ...

2021

Dictionary Learning for Two-Dimensional Kendall Shapes

Michaël Unser, Virginie Sophie Uhlmann, Julien René Pierre Fageot, Anna You-Lai Song

We propose a novel sparse dictionary learning method for planar shapes in the sense of Kendall, namely configurations of landmarks in the plane considered up to similitudes. Our shape dictionary method provides a good trade-off between algorithmic simplici ...

SIAM PUBLICATIONS2020

Wasserstein Distributionally Robust Learning

Soroosh Shafieezadeh Abadeh

Many decision problems in science, engineering, and economics are affected by uncertainty, which is typically modeled by a random variable governed by an unknown probability distribution. For many practical applications, the probability distribution is onl ...

EPFL2020

Chemiscope: interactive structure-property explorer for materials and molecules

Michele Ceriotti, Guillaume André Jean Fraux

The number of materials or molecules that can be created by combining different chemical elements in various proportions and spatial arrangements is enormous. Computational chemistry can be used to generate databases containing billions of potential struct ...

2020

Oblivious Sketching of High-Degree Polynomial Kernels

Mikhail Kapralov, Amir Zandieh

Kernel methods are fundamental tools in machine learning that allow detection of non-linear dependencies between data without explicitly constructing feature vectors in high dimensional spaces. A major disadvantage of kernel methods is their poor scalabili ...

ASSOC COMPUTING MACHINERY2020

On Perfect Clustering of High Dimension, Low Sample Size Data

Soham Sarkar

Popular clustering algorithms based on usual distance functions (e.g., the Euclidean distance) often suffer in high dimension, low sample size (HDLSS) situations, where concentration of pairwise distances and violation of neighborhood structure have advers ...

IEEE COMPUTER SOC2020

Graph Laplacian Mixture Model

Pascal Frossard, Hermina Petric Maretic

Graph learning methods have recently been receiving increasing interest as means to infer structure in datasets. Most of the recent approaches focus on different relationships between a graph and data sample distributions, mostly in settings where all avai ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

MOSES: A Streaming Algorithm for Linear Dimensionality Reduction

Armin Eftekhari

This paper introduces Memory-limited Online Subspace Estimation Scheme (MOSES) for both estimating the principal components of streaming data and reducing its dimension. More specifically, in various applications such as sensor networks, the data vectors a ...

IEEE COMPUTER SOC2020

Compute-Forward for DMCs: Simultaneous Decoding of Multiple Combinations

Michael Christoph Gastpar, Adriano Pastore, Sung Hoon Lim, Chen Feng

Algebraic network information theory is an emerging facet of network information theory, studying the achievable rates of random code ensembles that have algebraic structure, such as random linear codes. A distinguishing feature is that linear combinations ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020