Big data can be a blessing: with very large training data sets it becomes possible to perform
complex learning tasks with unprecedented accuracy. Yet, this improved performance …

We describe a general framework—compressive statistical learning—for resourceefficient
large-scale learning: the training collection is compressed in one pass into a …

In this article, we study the problem of recovering sparse spikes with over-parametrized
projected descent. We first provide a theoretical study of approximate recovery with our …

Single-photon lidar has become a prominent tool for depth imaging in recent years. At the
core of the technique, the depth of a target is measured by constructing a histogram of time …

The expected patch log-likelihood algorithm (EPLL) and its extensions have shown good
performances for image denoising. The prior model used by EPLL is usually a Gaussian …

Comparing probability distributions is at the crux of many machine learning algorithms.
Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of …

Compressive learning is an approach to efficient large scale learning based on sketching an
entire dataset to a single mean embedding (the sketch), ie a vector of generalized moments …

Assume that an unknown integral operator living in some known subspace is observed
indirectly, by evaluating its action on a discrete measure containing a few isolated Dirac …

We deal with two complementary questions about approximation properties of ReLU
networks. First, we study how the uniform quantization of ReLU networks with real-valued …

Solving ill-posed inverse problems can be done accurately if a regularizer well adapted to
the nature of the data is available. Such regularizer can be systematically linked with the …