Search Results for author:
Found 41 papers, 22 papers with code
Clifford-Steerable Convolutional Neural Networks
We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs.
Clifford Group Equivariant Simplicial Message Passing Networks
Experimental results show that our method is able to outperform both equivariant and simplicial graph neural networks on a variety of geometric tasks.
Designing Long-term Group Fair Policies in Dynamical Systems
Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term - even if fairness considerations were taken in the policy design process.
Anytime-Valid Confidence Sequences for Consistent Uncertainty Estimation in Early-Exit Neural Networks
Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass.
Deep anytime-valid hypothesis testing
We propose a general framework for constructing powerful, sequential hypothesis tests for a large class of nonparametric testing problems.
Lie Group Decompositions for Equivariant Neural Networks
Using the structure and geometry of Lie groups and their homogeneous spaces, we present a framework by which it is possible to work with such groups primarily focusing on the Lie groups $G = \text{GL}^{+}(n, \mathbb{R})$ and $G = \text{SL}(n, \mathbb{R})$, as well as their representation as affine transformations $\mathbb{R}^{n} \rtimes G$.
Simulation-based Inference with the Generalized Kullback-Leibler Divergence
The objective recovers Neural Posterior Estimation when the model class is normalized and unifies it with Neural Ratio Estimation, combining both into a single objective.
Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
Markov processes are widely used mathematical models for describing dynamic systems in various fields.
On the Effectiveness of Hybrid Mutual Information Estimation
Estimating the mutual information from samples from a joint distribution is a challenging problem in both science and engineering.
Balancing Simulation-based Inference for Conservative Posteriors
We show empirically that the balanced versions tend to produce conservative posterior approximations on a wide variety of benchmarks.
Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study
We propose parameterizing the population distribution of the gravitational wave population modeling framework (Hierarchical Bayesian Analysis) with a normalizing flow.
Physics-informed inference of aerial animal movements from weather radar data
Under the assumption that the latent system dynamics are well approximated by a locally linear Gaussian transition model, we perform efficient posterior estimation using the classical Kalman smoother.
E-Valuating Classifier Two-Sample Tests
Compared to $p$-values-based tests, tests with E-values have finite sample guarantees for the type I error.
Contrastive Neural Ratio Estimation
Likelihood-to-evidence ratio estimation is usually cast as either a binary (NRE-A) or a multiclass (NRE-B) classification task.
Equivariance-aware Architectural Optimization of Neural Networks
Incorporating equivariance to symmetry groups as a constraint during neural network training can improve performance and generalization for tasks exhibiting those symmetries, but such symmetries are often not perfectly nor explicitly present.
Multi-objective optimization via equivariant deep hypervolume approximation
We also apply and compare our methods to state-of-the-art multi-objective BO methods and EAs on a range of synthetic benchmark test cases.
Multi-View Independent Component Analysis with Shared and Individual Sources
Independent component analysis (ICA) is a blind source separation method for linear disentanglement of independent latent sources from observed data.
Disentangled Representations using Trained Models
With the help of the implicit function theorem we show how, using a diverse set of models that have already been trained on the data, to select a pair of data points that have a common value of interpretable factors.
Self-Supervised Inference in State-Space Models
Additionally, using an approximate conditional independence, we can perform smoothing without having to parameterize a separate model.
Truncated Marginal Neural Ratio Estimation
Parametric stochastic simulators are ubiquitous in science, often featuring high-dimensional input parameters and/or an intractable likelihood.
Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds
We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent.
An Information-theoretic Approach to Distribution Shifts
Safely deploying machine learning models to the real world is often a challenging process.
Transitional Conditional Independence
For this we introduce transition probability spaces and transitional random variables.
Combining Interventional and Observational Data Using Causal Reductions
Second, for continuous variables and assuming a linear-Gaussian model, we derive equality constraints for the parameters of the observational and interventional distributions.
Simplicial Regularization
Inspired by the fuzzy topological representation of a dataset employed in UMAP (McInnes et al., 2018), we propose a regularization principle for supervised learning based on the preservation of the simplicial complex structure of the data.
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
Argmax Flows are defined by a composition of a continuous distribution (such as a normalizing flow), and an argmax function.
Argmax Flows: Learning Categorical Distributions with Normalizing Flows
This paper introduces a new method to define and train continuous distributions such as normalizing flows directly on categorical data, for example text and image segmentation.
Self Normalizing Flows
Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework.
FlipOut: Uncovering Redundant Weights via Sign Flipping
Modern neural networks, although achieving state-of-the-art results on many tasks, tend to have a large number of parameters, which increases training time and resource usage.
Improving Fair Predictions Using Variational Inference In Causal Models
Recent work on fairness metrics shows the need for causal reasoning in fairness constraints.
Neural Ordinary Differential Equations on Manifolds
Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions.
Pruning via Iterative Ranking of Sensitivity Statistics
With the introduction of SNIP [arXiv:1810. 02340v2], it has been demonstrated that modern neural networks can effectively be pruned before training.
Selecting Data Augmentation for Simulating Interventions
We argue that causal concepts can be used to explain the success of data augmentation by describing how they can weaken the spurious correlation between the observed domains and the task labels.
Learning Robust Representations via Multi-View Information Bottleneck
This enables us to identify superfluous information as that not shared by both views.
Reparameterizing Distributions on Lie Groups
Unfortunately, this research has primarily focused on distributions defined in Euclidean space, ruling out the usage of one of the most influential class of spaces with non-trivial topologies: Lie groups.
Causal Calculus in the Presence of Cycles, Latent Confounders and Selection Bias
We prove the main rules of causal calculus (also called do-calculus) for i/o structural causal models (ioSCMs), a generalization of a recently proposed general class of non-/linear structural causal models that allow for cycles, latent confounders and arbitrary probability distributions.
Sinkhorn AutoEncoders
We show that minimizing the p-Wasserstein distance between the generator and the true data distribution is equivalent to the unconstrained min-min optimization of the p-Wasserstein distance between the encoder aggregated posterior and the prior in latent space, plus a reconstruction error.
Explorations in Homeomorphic Variational Auto-Encoding
Our experiments show that choosing manifold-valued latent variables that match the topology of the latent data manifold, is crucial to preserve the topological structure and learn a well-behaved latent space.
Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders
We address the problem of causal discovery from data, making use of the recently proposed causal modeling framework of modular structural causal models (mSCM) to handle cycles, latent confounders and non-linearities.
Markov Properties for Graphical Models with Cycles and Latent Variables
We investigate probabilistic graphical models that allow for both cycles and latent variables.
Foundations of Structural Causal Models with Cycles and Latent Variables
In this paper, we investigate SCMs in a more general setting, allowing for the presence of both latent confounders and cycles.
