274 citations · 423 across the 15 of their papers we have counts for
15 papers
AudioPaLM: A Large Language Model That Can Speak and Listen
Paul K. Rubenstein, Chulayuth Asawaroengchai, Duc Dung Nguyen +27
We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and…
Learning Translation Quality Evaluation on Low Resource Languages from Large Language Models
Amirkeivan Mohtashami, Mauro Verzetti, Paul K. Rubenstein
Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be…
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
Thomas Verelst, Paul K. Rubenstein, Marcin Eichner +2
As natural images usually contain multiple objects, multi-label image classification is more applicable "in the wild" than single-label classification. However, exhaustively annota…
Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks
Julius von Kügelgen, Paul K Rubenstein, Bernhard Schölkopf +1
We study the problem of causal discovery through targeted interventions. Starting from few observational measurements, we follow a Bayesian active learning approach to perform thos…
On Mutual Information Maximization for Representation Learning
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein +2
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different…
Practical and Consistent Estimation of f-Divergences
Paul K. Rubenstein, Olivier Bousquet, Josip Djolonga +2
The estimation of an f-divergence between two probability distributions based on samples is a fundamental problem in statistics and machine learning. Most works study this problem…
The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA
Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou +2
We consider the problem of recovering a common latent source with independent components from multiple views. This applies to settings in which a variable is measured with multiple…
An Empirical Study of Generative Models with Encoders
Paul K. Rubenstein, Yunpeng Li, Dominik Roblek
Generative adversarial networks (GANs) are capable of producing high quality image samples. However, unlike variational autoencoders (VAEs), GANs lack encoders that provide the inv…
Structural causal models for macro-variables in time-series
Dominik Janzing, Paul Rubenstein, Bernhard Schölkopf
We consider a bivariate time series that is given by a simple linear autoregressive model. Assuming that the equations describing each variable as a linear combination…
On the Latent Space of Wasserstein Auto-Encoders
Paul K. Rubenstein, Bernhard Schoelkopf, Ilya Tolstikhin
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should b…
Causal Consistency of Structural Equation Models
Paul K. Rubenstein, Sebastian Weichwald, Stephan Bongers +4
Complex systems can be modelled at various levels of detail. Ideally, causal models of the same system should be consistent with one another in the sense that they agree in their p…
Probabilistic Active Learning of Functions in Structural Causal Models
Paul K. Rubenstein, Ilya Tolstikhin, Philipp Hennig +1
We consider the problem of learning the functions computing children from parents in a Structural Causal Model once the underlying causal graph has been identified. This is in some…
From Deterministic ODEs to Dynamic Structural Causal Models
Paul K. Rubenstein, Stephan Bongers, Bernhard Schoelkopf +1
Structural Causal Models are widely used in causal modelling, but how they relate to other modelling tools is poorly understood. In this paper we provide a novel perspective on the…
A Kernel Test for Three-Variable Interactions with Random Processes
Paul K. Rubenstein, Kacper P. Chwialkowski, Arthur Gretton
We apply a wild bootstrap method to the Lancaster three-variable interaction measure in order to detect factorisation of the joint distribution on three variables forming a station…
The VC-Dimension of Similarity Hypotheses Spaces
Mark Herbster, Paul Rubenstein, James Townsend
Given a set and a function which labels each element of with either or , we may define a function to measure the similarity of…