Found 8 document(s)
Page 1 of 1
-
This work studies the estimation of many statistical quantiles under differential privacy. More precisely, given a distribution and access to i.i.d. samples from it, we study the estimation of the inverse of its cumulati...
-
We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learning of image representations. Besides bei...
-
This paper presents new theoretical results on sparse recovery guarantees fora greedy algorithm, Orthogonal Matching Pursuit (OMP), in the context ofcontinuous parametric dictionaries. Here, the continuous setting means ...
-
We discuss a long-lasting {\em qui pro quo} between regularization-based and Bayesian-based approaches to inverse problems, and review some recent results that try to reconcile both viewpoints. This sheds light on some t...
-
We consider the Gaussian framework for reverberant audio source separation, where the sources are modeled in the time-frequency domain by their short-term power spectra and their spatial covariance matrices. We propose t...
-
In this paper, we address the problem of noise compensation in speech signals for robust speech recognition. Several classical denoising methods in the field of speech and signal processing are compared on speech corrupt...
-
We study the approximation properties of wavelet bi-frame systems in Lp(R^d). For wavelet bi-frame systems the approximation spaces associated with best m-term approximation are completely characterized for a certain ran...
-
We study various approximation classes associated with m-term approximation by elements from a (possibly redundant) dictionary in a Banach space. The standard approximation class associated with the best m-term approxima...