Timezone: »
Poster
Hierarchical Methods of Moments
Matteo Ruffini · Guillaume Rabusseau · Borja Balle
Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models. Despite their theoretical appeal, the applicability of these methods to real data is still limited due to a lack of robustness to model misspecification. In this paper we present a hierarchical approach to methods of moments to circumvent such limitations. Our method is based on replacing the tensor decomposition step used in previous algorithms with approximate joint diagonalization. Experiments on topic modeling show that our method outperforms previous tensor decomposition methods in terms of speed and model quality.
Author Information
Matteo Ruffini (UPC)
Guillaume Rabusseau (Université de Montréal - Mila)
Borja Balle (DeepMind)
More from the Same Authors
-
2021 Spotlight: Lower and Upper Bounds on the Pseudo-Dimension of Tensor Network Models »
Behnoush Khavari · Guillaume Rabusseau -
2021 : Reconstructing Training Data with Informed Adversaries »
Borja Balle · Giovanni Cherubin · Jamie Hayes -
2021 : Few Shot Image Generation via Implicit Autoencoding of Support Sets »
Shenyang Huang · Kuan-Chieh Wang · Guillaume Rabusseau · Alireza Makhzani -
2023 Poster: Bounding training data reconstruction in DP-SGD »
Jamie Hayes · Borja Balle · Saeed Mahloujifar -
2022 : Panel on Privacy and Security in Machine Learning Systems »
Graham Cormode · Borja Balle · Yu-Xiang Wang · Alejandro Saucedo · Neil Lawrence -
2021 Workshop: Privacy in Machine Learning (PriML) 2021 »
Yu-Xiang Wang · Borja Balle · Giovanni Cherubin · Kamalika Chaudhuri · Antti Honkela · Jonathan Lebensold · Casey Meehan · Mi Jung Park · Adrian Weller · Yuqing Zhu -
2021 Poster: Lower and Upper Bounds on the Pseudo-Dimension of Tensor Network Models »
Behnoush Khavari · Guillaume Rabusseau -
2020 : Invited Talk 9 Q&A by Guillaume »
Guillaume Rabusseau -
2020 : Invited Talk 9: Tensor Network Models for Structured Data »
Guillaume Rabusseau -
2020 : Panel Discussion 1: Theoretical, Algorithmic and Physical »
Jacob Biamonte · Ivan Oseledets · Jens Eisert · Nadav Cohen · Guillaume Rabusseau · Xiao-Yang Liu -
2020 Workshop: Privacy Preserving Machine Learning - PriML and PPML Joint Edition »
Borja Balle · James Bell · Aurélien Bellet · Kamalika Chaudhuri · Adria Gascon · Antti Honkela · Antti Koskela · Casey Meehan · Olga Ohrimenko · Mi Jung Park · Mariana Raykova · Mary Anne Smart · Yu-Xiang Wang · Adrian Weller -
2020 Poster: Privacy Amplification via Random Check-Ins »
Borja Balle · Peter Kairouz · Brendan McMahan · Om Thakkar · Abhradeep Guha Thakurta -
2019 Workshop: Privacy in Machine Learning (PriML) »
Borja Balle · Kamalika Chaudhuri · Antti Honkela · Antti Koskela · Casey Meehan · Mi Jung Park · Mary Anne Smart · Mary Anne Smart · Adrian Weller -
2019 Poster: Privacy Amplification by Mixing and Diffusion Mechanisms »
Borja Balle · Gilles Barthe · Marco Gaboardi · Joseph Geumlek -
2018 Poster: Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences »
Borja Balle · Gilles Barthe · Marco Gaboardi -
2017 : Poster Session (encompasses coffee break) »
Beidi Chen · Borja Balle · Daniel Lee · iuri frosio · Jitendra Malik · Jan Kautz · Ke Li · Masashi Sugiyama · Miguel A. Carreira-Perpinan · Ramin Raziperchikolaei · Theja Tulabandhula · Yung-Kyun Noh · Adams Wei Yu -
2017 Poster: Multitask Spectral Learning of Weighted Automata »
Guillaume Rabusseau · Borja Balle · Joelle Pineau -
2016 Workshop: Private Multi-Party Machine Learning »
Borja Balle · Aurélien Bellet · David Evans · Adrià Gascón -
2016 Poster: Low-Rank Regression with Tensor Responses »
Guillaume Rabusseau · Hachem Kadri