Author name cluster

Michel Besserve

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

20 papers

2 author rows

UAI Conference 2024 Conference Paper

Targeted Reduction of Causal Models

Armin Kekic
Bernhard Schölkopf
Michel Besserve

Why does a phenomenon occur? Addressing this question is central to most scientific inquiries and often relies on simulations of scientific models. As models become more intricate, deciphering the causes behind phenomena in high-dimensional spaces of interconnected variables becomes increasingly challenging. Causal Representation Learning (CRL) offers a promising avenue to uncover interpretable causal patterns within these simulations through an interventional lens. However, developing general CRL frameworks suitable for practical applications remains an open challenge. We introduce _Targeted Causal Reduction_ (TCR), a method for condensing complex intervenable models into a concise set of causal factors that explain a specific target phenomenon. We propose an information theoretic objective to learn TCR from interventional data of simulations, establish identifiability for continuous variables under shift interventions and present a practical algorithm for learning TCRs. Its ability to generate interpretable high-level explanations from complex models is demonstrated on toy and mechanical systems, illustrating its potential to assist scientists in the study of complex phenomena in a broad range of disciplines.

Details

NeurIPS Conference 2023 Conference Paper

Causal Component Analysis

Liang Wendong
Armin Kekić
Julius von Kügelgen
Simon Buchholz
Michel Besserve
Luigi Gresele
Bernhard Schölkopf

Independent Component Analysis (ICA) aims to recover independent latent variables from observed mixtures thereof. Causal Representation Learning (CRL) aims instead to infer causally related (thus often statistically dependent ) latent variables, together with the unknown graph encoding their causal relationships. We introduce an intermediate problem termed Causal Component Analysis (CauCA). CauCA can be viewed as a generalization of ICA, modelling the causal dependence among the latent components, and as a special case of CRL. In contrast to CRL, it presupposes knowledge of the causal graph, focusing solely on learning the unmixing function and the causal mechanisms. Any impossibility results regarding the recovery of the ground truth in CauCA also apply for CRL, while possibility results may serve as a stepping stone for extensions to CRL. We characterize CauCA identifiability from multiple datasets generated through different types of interventions on the latent causal variables. As a corollary, this interventional perspective also leads to new identifiability results for nonlinear ICA—a special case of CauCA with an empty graph—requiring strictly fewer datasets than previous results. We introduce a likelihood-based approach using normalizing flows to estimate both the unmixing function and the causal mechanisms, and demonstrate its effectiveness through extensive synthetic experiments in the CauCA and ICA setting.

PDF Details

ICML Conference 2023 Conference Paper

Homomorphism AutoEncoder - Learning Group Structured Representations from Observed Transitions

Hamza Keurti
Hsiao-Ru Pan
Michel Besserve
Benjamin F. Grewe
Bernhard Schölkopf

How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional knowledge, we study this problem using tools from representation learning and group theory. We propose methods enabling an agent acting upon the world to learn internal representations of sensory information that are consistent with actions that modify it. We use an autoencoder equipped with a group representation acting on its latent space, trained using an equivariance-derived loss in order to enforce a suitable homomorphism property on the group representation. In contrast to existing work, our approach does not require prior knowledge of the group and does not restrict the set of actions the agent can perform. We motivate our method theoretically, and show empirically that it can learn a group representation of the actions, thereby capturing the structure of the set of transformations applied to the environment. We further show that this allows agents to predict the effect of sequences of future actions with improved accuracy.

Details

NeurIPS Conference 2023 Conference Paper

Nonparametric Identifiability of Causal Representations from Unknown Interventions

Julius von Kügelgen
Michel Besserve
Liang Wendong
Luigi Gresele
Armin Kekić
Elias Bareinboim
David Blei
Bernhard Schölkopf

We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior work relies on weak supervision, in the form of counterfactual pre- and post-intervention views or temporal structure; places restrictive assumptions, such as linearity, on the mixing function or latent causal model; or requires partial knowledge of the generative process, such as the causal graph or intervention targets. We instead consider the general setting in which both the causal model and the mixing function are nonparametric. The learning signal takes the form of multiple datasets, or environments, arising from unknown interventions in the underlying causal model. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data. We study the fundamental setting of two causal variables and prove that the observational distribution and one perfect intervention per node suffice for identifiability, subject to a genericity condition. This condition rules out spurious solutions that involve fine-tuning of the intervened and observational distributions, mirroring similar conditions for nonlinear cause-effect inference. For an arbitrary number of variables, we show that at least one pair of distinct perfect interventional domains per node guarantees identifiability. Further, we demonstrate that the strengths of causal influences among the latent variables are preserved by all equivalent solutions, rendering the inferred representation appropriate for drawing causal conclusions from new data. Our study provides the first identifiability results for the general nonparametric setting with unknown interventions, and elucidates what is possible and impossible for causal representation learning without more direct supervision.

PDF Details

ICLR Conference 2023 Conference Paper

Structure by Architecture: Structured Representations without Regularization

Felix Leeb
Giulia Lanzillotta
Yashas Annadani
Michel Besserve
Stefan Bauer
Bernhard Schölkopf

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior distribution for sampling, we propose a sampling technique that relies solely on the independence of latent variables, thereby avoiding the trade-off between reconstruction quality and generative performance typically observed in VAEs. We design a novel autoencoder architecture capable of learning a structured representation without the need for aggressive regularization. Our structural decoders learn a hierarchy of latent variables, thereby ordering the information without any additional regularization or supervision. We demonstrate how these models learn a representation that improves results in a variety of downstream tasks including generation, disentanglement, and extrapolation using several challenging and natural image datasets.

Details

TMLR Journal 2022 Journal Article

Causal Feature Selection via Orthogonal Search

Ashkan Soleymani
Anant Raj
Stefan Bauer
Bernhard Schölkopf
Michel Besserve

The problem of inferring the direct causal parents of a response variable among a large set of explanatory variables is of high practical importance in many disciplines. However, established approaches often scale at least exponentially with the number of explanatory variables, are difficult to extend to nonlinear relationships and are difficult to extend to cyclic data. Inspired by debiased machine learning methods, we study a one-vs.-the-rest feature selection approach to discover the direct causal parent of the response. We propose an algorithm that works for purely observational data while also offering theoretical guarantees, including the case of partially nonlinear relationships possibly under the presence of cycles. As it requires only one estimation for each variable, our approach is applicable even to large graphs. We demonstrate significant improvements compared to established approaches.

PDF Details

CLeaR Conference 2022 Conference Paper

Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations

Michel Besserve
Naji Shajarisales
Dominik Janzing
Bernhard Sch\"olkopf

Distinguishing between cause and effect using time series observational data is a major challenge in many scientific fields. A new perspective has been provided based on the principle of Independence of Causal Mechanisms (ICM), leading to the Spectral Independence Criterion (SIC) for time series causally unidirectionally linked by a linear time-invariant relation. SIC postulates that the power spectral density (PSD) of the cause time series is \it uncorrelated with the squared modulus of the frequency response of the filter generating the effect. Since SIC rests on methods and assumptions in stark contrast with most causal discovery methods for time series, it raises questions regarding what theoretical grounds justify its use. In this paper, we provide answers covering several key aspects. After providing an information theoretic interpretation of SIC, we present an identifiability result that sheds light on the context for which this approach is expected to perform well. We further demonstrate the robustness of SIC to downsampling – an obstacle that can spoil Granger-based inference. Finally, an invariance perspective allows to explore the limitations of the spectral independence assumption and how to generalize it. Overall, these results provide insights on how the ICM principle can be assessed mathematically to infer direction of causation in empirical time series.

PDF Details

NeurIPS Conference 2022 Conference Paper

Embrace the Gap: VAEs Perform Independent Mechanism Analysis

Patrik Reizinger
Luigi Gresele
Jack Brady
Julius von Kügelgen
Dominik Zietlow
Bernhard Schölkopf
Georg Martius
Wieland Brendel

Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidence lower bound (ELBO), at the expense of a gap to the exact (log-)marginal likelihood. While VAEs are commonly used for representation learning, it is unclear why ELBO maximization would yield useful representations, since unregularized maximum likelihood estimation cannot invert the data-generating process. Yet, VAEs often succeed at this task. We seek to elucidate this apparent paradox by studying nonlinear VAEs in the limit of near-deterministic decoders. We first prove that, in this regime, the optimal encoder approximately inverts the decoder---a commonly used but unproven conjecture---which we refer to as self-consistency. Leveraging self-consistency, we show that the ELBO converges to a regularized log-likelihood. This allows VAEs to perform what has recently been termed independent mechanism analysis (IMA): it adds an inductive bias towards decoders with column-orthogonal Jacobians, which helps recovering the true latent factors. The gap between ELBO and log-likelihood is therefore welcome, since it bears unanticipated benefits for nonlinear representation learning. In experiments on synthetic and image data, we show that VAEs uncover the true latent factors when the data generating process satisfies the IMA assumption.

PDF Details

NeurIPS Conference 2022 Conference Paper

Exploring the Latent Space of Autoencoders with Interventional Assays

Felix Leeb
Stefan Bauer
Michel Besserve
Bernhard Schölkopf

Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the representation is usually uninterpretable, making analysis and principled progress challenging. We propose a framework, called latent responses, which exploits the locally contractive behavior exhibited by variational autoencoders to explore the learned manifold. More specifically, we develop tools to probe the representation using interventions in the latent space to quantify the relationships between latent variables. We extend the notion of disentanglement to take the learned generative process into account and consequently avoid the limitations of existing metrics that may rely on spurious correlations. Our analyses underscore the importance of studying the causal structure of the representation to improve performance on downstream tasks such as generation, interpolation, and inference of the factors of variation.

PDF Details

NeurIPS Conference 2022 Conference Paper

Function Classes for Identifiable Nonlinear Independent Component Analysis

Simon Buchholz
Michel Besserve
Bernhard Schölkopf

Unsupervised learning of latent variable models (LVMs) is widely used to represent data in machine learning. When such model reflects the ground truth factors and the mechanisms mapping them to observations, there is reason to expect that such models allow generalisation in downstream tasks. It is however well known that such identifiability guaranties are typically not achievable without putting constraints on the model class. This is notably the case for nonlinear Independent Component Analysis, in which the LVM maps statistically independent variables to observations via a deterministic nonlinear function. Several families of spurious solutions fitting perfectly the data, but that do not correspond to the ground truth factors can be constructed in generic settings. However, recent work suggests that constraining the function class of such models may promote identifiability. Specifically, function classes with constraints on their partial derivatives, gathered in the Jacobian matrix, have been proposed, such as orthogonal coordinate transformations (OCT), which impose orthogonality of the Jacobian columns. In the present work, we prove that a subclass of these transformations, conformal maps, is identifiable and provide novel theoretical results suggesting that OCTs have properties that prevent families of spurious solutions to spoil identifiability in a generic setting.

PDF Details

UAI Conference 2022 Conference Paper

Learning soft interventions in complex equilibrium systems

Michel Besserve
Bernhard Schölkopf

Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.

Details

AAAI Conference 2021 Conference Paper

A Theory of Independent Mechanisms for Extrapolation in Generative Models

Michel Besserve
Remy Sun
Dominik Janzing
Bernhard Schölkopf

Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments? An intuitive idea to promote such extrapolation capabilities is to have the architecture of such model reflect a causal graph of the true data generating process, such that one can intervene on each node independently of the others. However, the nodes of this graph are usually unobserved, leading to overparameterization and lack of identifiability of the causal structure. We develop a theoretical framework to address this challenging situation by defining a weaker form of identifiability, based on the principle of independence of mechanisms. We demonstrate on toy examples that classical stochastic gradient descent can hinder the model’s extrapolation capabilities, suggesting independence of mechanisms should be enforced explicitly during training. Experiments on deep generative models trained on real world data support these insights and illustrate how the extrapolation capabilities of such models can be leveraged.

PDF Details

NeurIPS Conference 2021 Conference Paper

Independent mechanism analysis, a new concept?

Luigi Gresele
Julius von Kügelgen
Vincent Stimper
Bernhard Schölkopf
Michel Besserve

Independent component analysis provides a principled framework for unsupervised representation learning, with solid theory on the identifiability of the latent code that generated the data, given only observations of mixtures thereof. Unfortunately, when the mixing is nonlinear, the model is provably nonidentifiable, since statistical independence alone does not sufficiently constrain the problem. Identifiability can be recovered in settings where additional, typically observed variables are included in the generative process. We investigate an alternative path and consider instead including assumptions reflecting the principle of independent causal mechanisms exploited in the field of causality. Specifically, our approach is motivated by thinking of each source as independently influencing the mixing process. This gives rise to a framework which we term independent mechanism analysis. We provide theoretical and empirical evidence that our approach circumvents a number of nonidentifiability issues arising in nonlinear blind source separation.

PDF Details

NeurIPS Conference 2021 Conference Paper

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

Julius von Kügelgen
Yash Sharma
Luigi Gresele
Wieland Brendel
Bernhard Schölkopf
Michel Besserve
Francesco Locatello

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek to understand the empirical success of this approach from a theoretical perspective. We formulate the augmentation process as a latent variable model by postulating a partition of the latent representation into a content component, which is assumed invariant to augmentation, and a style component, which is allowed to change. Unlike prior work on disentanglement and independent component analysis, we allow for both nontrivial statistical and causal dependencies in the latent space. We study the identifiability of the latent representation based on pairs of views of the observations and prove sufficient conditions that allow us to identify the invariant content partition up to an invertible mapping in both generative and discriminative settings. We find numerical simulations with dependent latent variables are consistent with our theory. Lastly, we introduce Causal3DIdent, a dataset of high-dimensional, visually complex images with rich causal dependencies, which we use to study the effect of data augmentations performed in practice.

PDF Details

ICLR Conference 2020 Conference Paper

Counterfactuals uncover the modular structure of deep generative models

Michel Besserve
Arash Mehrjou
Rémy Sun
Bernhard Schölkopf

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervision. While previous work has focused on exploiting statistical independence to \textit{disentangle} latent factors, we argue that such requirement can be advantageously relaxed and propose instead a non-statistical framework that relies on identifying a modular organization of the network, based on counterfactual manipulations. Our experiments support that modularity between groups of channels is achieved to a certain degree on a variety of generative models. This allowed the design of targeted interventions on complex image datasets, opening the way to applications such as computationally efficient style transfer and the automated assessment of robustness to contextual changes in pattern recognition systems.

Details

UAI Conference 2019 Conference Paper

Coordinating Users of Shared Facilities via Data-driven Predictive Assistants and Game Theory

Philipp Geiger
Michel Besserve
Justus Winkelmann
Claudius Proissl
Bernhard Schölkopf

We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.), to support coordination between them, and increase efficiency of such collective systems. Key questions are: (1) when and how much can (accurate) predictions help for coordination, and (2) which assistant algorithms reach optimal predictions? First we lay conceptual ground for this setting where user preferences are a priori unknown and predictions influence outcomes. Addressing (1), we establish conditions under which self-fulfilling prophecies, i. e. , “perfect” (probabilistic) predictions of what will happen, solve the coordination problem in the gametheoretic sense of selecting a Bayesian Nash equilibrium (BNE). Next we prove that such prophecies exist even in large-scale settings where only aggregated statistics about users are available. This entails a new (nonatomic) BNE existence result. Addressing (2), we propose two assistant algorithms that sequentially learn from users’ reactions, together with optimality/ convergence guarantees. We validate one of them in a large real-world experiment.

Details

ICML Conference 2015 Conference Paper

Telling cause from effect in deterministic linear dynamical systems

Naji Shajarisales
Dominik Janzing
Bernhard Schölkopf
Michel Besserve

Telling a cause from its effect using observed time series data is a major challenge in natural and social sciences. Assuming the effect is generated by the cause through a linear system, we propose a new approach based on the hypothesis that nature chooses the “cause” and the “mechanism generating the effect from the cause” independently of each other. Specifically we postulate that the power spectrum of the “cause” time series is uncorrelated with the square of the frequency response of the linear filter (system) generating the effect. While most causal discovery methods for time series mainly rely on the noise, our method relies on asymmetries of the power spectral density properties that exist even in deterministic systems. We describe mathematical assumptions in a deterministic model under which the causal direction is identifiable. In particular, we show a scenario where the method works but Granger causality fails. Experiments show encouraging results on synthetic as well as real-world data. Overall, this suggests that the postulate of Independence of Cause and Mechanism is a promising principle for causal inference on observed time series.

Details

NeurIPS Conference 2013 Conference Paper

Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators.

Michel Besserve
Nikos Logothetis
Bernhard Schölkopf

Many applications require the analysis of complex interactions between time series. These interactions can be non-linear and involve vector valued as well as complex data structures such as graphs or strings. Here we provide a general framework for the statistical analysis of these interactions when random variables are sampled from stationary time-series of arbitrary objects. To achieve this goal we analyze the properties of the kernel cross-spectral density operator induced by positive definite kernels on arbitrary input domains. This framework enables us to develop an independence test between time series as well as a similarity measure to compare different types of coupling. The performance of our test is compared to the HSIC test using i. i. d. assumptions, showing improvement in terms of detection errors as well as the suitability of this approach for testing dependency in complex dynamical systems. Finally, we use this approach to characterize complex interactions in electrophysiological neural time series.

PDF Details

NeurIPS Conference 2012 Conference Paper

Towards a learning-theoretic analysis of spike-timing dependent plasticity

David Balduzzi
Michel Besserve

This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to theoretical analysis. We show that the selectron encodes reward estimates into spikes and that an error bound on spikes is controlled by a spiking margin and the sum of synaptic weights. Moreover, the efficacy of spikes (their usefulness to other reward maximizing selectrons) also depends on total synaptic strength. Finally, based on our analysis, we propose a regularized version of STDP, and show the regularization improves the robustness of neuronal learning when faced with multiple stimuli.

PDF Details

YNIMG Journal 2011 Journal Article

Improving quantification of functional networks with EEG inverse problem: Evidence from a decoding point of view

Michel Besserve
Jacques Martinerie
Line Garnero

Decoding experimental conditions from single trial Electroencephalographic (EEG) signals is becoming a major challenge for the study of brain function and real-time applications such as Brain Computer Interface. EEG source reconstruction offers principled ways to estimate the cortical activities from EEG signals. But to what extent it can enhance informative brain signals in single trial has not been addressed in a general setting. We tested this using the minimum norm estimate solution (MNE) to estimate spectral power and coherence features at the cortical level. With a fast implementation, we computed a support vector machine (SVM) classifier output from these quantities in real-time, without prior on the relevant functional networks. We applied this approach to single trial decoding of ongoing mental imagery tasks using EEG data recorded in 5 subjects. Our results show that reconstructing the underlying cortical network dynamics significantly outperforms a usual electrode level approach in terms of information transfer and also reduces redundancy between coherence and power features, supporting a decrease of volume conduction effects. Additionally, the classifier coefficients reflect the most informative features of network activity, showing an important contribution of localized motor and sensory brain areas, and of coherence between areas up to 6cm distance. This study provides a computationally efficient and interpretable strategy to extract information from functional networks at the cortical level in single trial. Moreover, this sets a general framework to evaluate the performance of EEG source reconstruction methods by their decoding abilities.

Details DOI