output
20192023
most citedMusic Source Separation in the Waveform Domain

185 citations

12 papers

math.OC2023★ 1 cited

Nonlinear conjugate gradient methods: worst-case convergence rates via computer-assisted analyses

Shuvomoy Das Gupta, Robert M. Freund, Xu Andy Sun +1

We propose a computer-assisted approach to the analysis of the worst-case convergence of nonlinear conjugate gradient methods (NCGMs). Those methods are known for their generally g…

math.OC2022

Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity

Eduard Gorbunov, Adrien Taylor, Samuel Horváth +1

Algorithms for min-max optimization and variational inequalities are often studied under monotonicity assumptions. Motivated by non-monotone machine learning applications, we follo…

math.OC2022

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

Benjamin Dubois-Taine, Francis Bach, Quentin Berthet +1

We consider the problem of minimizing the sum of two convex functions. One of those functions has Lipschitz-continuous gradients, and can be accessed via stochastic oracles, wherea…

math.OC2021★ 3 cited

Super-Acceleration with Cyclical Step-sizes

Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut +2

We develop a convergence-rate analysis of momentum with cyclical step-sizes. We show that under some assumption on the spectral gap of Hessians in machine learning, cyclical step-s…

cs.LG2021

On the Consistency of Max-Margin Losses

Alex Nowak-Vila, Alessandro Rudi, Francis Bach

The foundational concept of Max-Margin in machine learning is ill-posed for output spaces with more than two labels such as in structured prediction. In this paper, we show that th…

cs.SD2021★ 30 cited

Self-Supervised VQ-VAE for One-Shot Music Style Transfer

Ondřej Cífka, Alexey Ozerov, Umut Şimşekli +1

Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its intr…