Search Results for author: Gaspar Rochette

Found 6 papers, 4 papers with code

Efficient Per-Example Gradient Computations in Convolutional Neural Networks

1 code implementation12 Dec 2019 Gaspar Rochette, Andre Manoel, Eric W. Tramel

One notable application comes from the field of differential privacy, where per-example gradients must be norm-bounded in order to limit the impact of each example on the aggregated batch gradient.

Scale Dependencies and Self-Similar Models with Wavelet Scattering Spectra

3 code implementations19 Apr 2022 Rudy Morel, Gaspar Rochette, Roberto Leonarduzzi, Jean-Philippe Bouchaud, Stéphane Mallat

We introduce the wavelet scattering spectra which provide non-Gaussian models of time-series having stationary increments.

Time Series Time Series Analysis

Phase Harmonic Correlations and Convolutional Neural Networks

1 code implementation29 Oct 2018 Stéphane Mallat, Sixin Zhang, Gaspar Rochette

For wavelet filters, we show numerically that signals having sparse wavelet coefficients can be recovered from few phase harmonic correlations, which provide a compressive representation

Time Series Time Series Analysis

An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models

no code implementations20 Jun 2022 Rahil Parikh, Gaspar Rochette, Carol Espy-Wilson, Shihab Shamma

Knowing that harmonicity is a critical cue for these networks to group sources, in this work, we perform a thorough investigation on ConvTasnet and DPT-Net to analyze how they perform a harmonic analysis of the input mixture.

Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.