767 citations · 1.8k across the 46 of their papers we have counts for
36 papers · 1 filter
Causal Discovery Under Hard Selection Bias: A New Robust Score-Matching Approach
Yiwen Qiu, Francesco Montagna, Shimeng Huang +1
Selection bias is a difficult yet widespread problem in causal discovery, occurring whenever non-random selection processes lead to data that is not representative of the underlyin…
Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models
Dario Rancati, Max Welling, Francesco Locatello
Causal modeling of physical temporal phenomena must handle interventions that act along trajectories, nonstationary induced laws, path-dependent effects, and feedback mediated by d…
Controlling Transient Amplification Improves Long-horizon Rollouts
Adeel Pervez, Francesco Locatello
Autoregressive neural simulators now match classical solvers on short-horizon prediction of physical systems, yet their accuracy degrades rapidly when rolled out over long horizons…
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
Tommaso Mencattini, Francesco Montagna, Francesco Locatello
Sparse Autoencoders (SAEs) that can accurately reconstruct their input (minimizing distortion) by making efficient use of few features (minimizing the rate) often fail to learn mon…
Learning Discrete Diffusion of Graphs via Free-Energy Gradient Flows
Dario Rancati, Jan Maas, Francesco Locatello
Diffusion-based models on continuous spaces have seen substantial recent progress through the mathematical framework of gradient flows, leveraging the Wasserstein-2 () metri…
Self-Compatibility: Evaluating Causal Discovery without Ground Truth
Philipp M. Faller, Leena Chennuru Vankadara, Atalanti A. Mastakouri +2
As causal ground truth is incredibly rare, causal discovery algorithms are commonly only evaluated on simulated data. This is concerning, given that simulations reflect preconcepti…
Benign Overfitting in Deep Neural Networks under Lazy Training
Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos +2
This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve B…
Scalable Causal Discovery with Score Matching
Francesco Montagna, Nicoletta Noceti, Lorenzo Rosasco +2
This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveragi…
Causal Discovery with Score Matching on Additive Models with Arbitrary Noise
Francesco Montagna, Nicoletta Noceti, Lorenzo Rosasco +2
Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in o…
Relative representations enable zero-shot latent space communication
Luca Moschella, Valentino Maiorca, Marco Fumero +3
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the…
Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks
Michael Lohaus, Matthäus Kleindessner, Krishnaram Kenthapadi +2
We show that deep networks trained to satisfy demographic parity often do so through a form of race or gender awareness, and that the more we force a network to be fair, the more a…
Score matching enables causal discovery of nonlinear additive noise models
Paul Rolland, Volkan Cevher, Matthäus Kleindessner +4
This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a bu…
Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization
Gideon Dresdner, Maria-Luiza Vladarean, Gunnar Rätsch +3
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this…
Dynamic Inference with Neural Interpreters
Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi +4
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalizat…
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
Osama Makansi, Julius von Kügelgen, Francesco Locatello +4
Predicting the future trajectory of a moving agent can be easy when the past trajectory continues smoothly but is challenging when complex interactions with other agents are involv…
Backward-Compatible Prediction Updates: A Probabilistic Approach
Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner +3
When machine learning systems meet real world applications, accuracy is only one of several requirements. In this paper, we assay a complementary perspective originating from the i…
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
Lukas Schott, Julius von Kügelgen, Frederik Träuble +6
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the wo…
Generalization and Robustness Implications in Object-Centric Learning
Andrea Dittadi, Samuele Papa, Michele De Vita +3
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed represe…
Neighborhood Contrastive Learning Applied to Online Patient Monitoring
Hugo Yèche, Gideon Dresdner, Francesco Locatello +2
Intensive care units (ICU) are increasingly looking towards machine learning for methods to provide online monitoring of critically ill patients. In machine learning, online monito…
Boosting Variational Inference With Locally Adaptive Step-Sizes
Gideon Dresdner, Saurav Shekhar, Fabian Pedregosa +2
Variational Inference makes a trade-off between the capacity of the variational family and the tractability of finding an approximate posterior distribution. Instead, Boosting Vari…
Towards Causal Representation Learning
Bernhard Schölkopf, Francesco Locatello, Stefan Bauer +4
The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit…
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
Francesco Locatello, Stefan Bauer, Mario Lucic +4
The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be…
On the Transfer of Disentangled Representations in Realistic Settings
Andrea Dittadi, Frederik Träuble, Francesco Locatello +5
Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disent…
A Commentary on the Unsupervised Learning of Disentangled Representations
Francesco Locatello, Stefan Bauer, Mario Lucic +4
The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In…