Anastasia Podosinnikova — accepted AI-conference papers

2019

Overcomplete Independent Component Analysis via SDP

Anastasia Podosinnikova, Amelia Perry, Alexander S. Wein, Francis Bach, Alexandre d’Aspremont, David Sontag

AISTATS 2019poster

We present a novel algorithm for overcomplete independent components analysis (ICA), where the number of latent sources k exceeds the dimension p of observed variables. Previous algorithms either suffer from high computational complexity or make strong assumptions about the form of the mixing matrix…

Cited by 28 Source ↗PDF ↗Scholar ↗

2016

Beyond CCA: Moment Matching for Multi-View Models

Anastasia Podosinnikova, Francis Bach, Simon Lacoste-Julien

ICML 2016poster

We introduce three novel semi-parametric extensions of probabilistic canonical correlation analysis with identifiability guarantees. We consider moment matching techniques for estimation in these models. For that, by drawing explicit links between the new models and a discrete version of independent…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2015

Rethinking LDA: Moment Matching for Discrete ICA

Anastasia Podosinnikova, Francis Bach, Simon Lacoste-Julien

NeurIPS 2015poster

We consider moment matching techniques for estimation in Latent Dirichlet Allocation (LDA). By drawing explicit links between LDA and discrete versions of independent component analysis (ICA), we first derive a new set of cumulant-based tensors, with an improved sample complexity. Moreover, we reuse…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗