Search Results for author:
Found 38 papers, 10 papers with code
Causal Coordinated Concurrent Reinforcement Learning
In this work, we propose a novel algorithmic framework for data sharing and coordinated exploration for the purpose of learning more data-efficient and better performing policies under a concurrent reinforcement learning (CRL) setting.
Causal Discovery by Kernel Deviance Measures with Heterogeneous Transforms
To go about capturing these discrepancies between cause and effect remains to be a challenge and many current state-of-the-art algorithms propose to compare the norms of the kernel mean embeddings of the conditional distributions.
Convergence guarantee for consistency models
We provide the first convergence guarantees for the Consistency Models (CMs), a newly emerging type of one-step generative models that can generate comparable samples to those generated by Diffusion Models.
Efficient Bayesian Optimization with Deep Kernel Learning and Transformer Pre-trained on Multiple Heterogeneous Datasets
Bayesian optimization (BO) is widely adopted in black-box optimization problems and it relies on a surrogate model to approximate the black-box response function.
Reweighted Interacting Langevin Diffusions: an Accelerated Sampling Methodfor Optimization
We proposed a new technique to accelerate sampling methods for solving difficult optimization problems.
Neighbor Auto-Grouping Graph Neural Networks for Handover Parameter Configuration in Cellular Network
This performance relies heavily on the configuration of the network parameters.
Reframed GES with a Neural Conditional Dependence Measure
In this paper, we revisit the Greedy Equivalence Search (GES) algorithm, which is widely cited as a score-based algorithm for learning the MEC of the underlying causal structure.
Out-of-distribution Generalization with Causal Invariant Transformations
In this work, we obviate these assumptions and tackle the OOD problem without explicitly recovering the causal feature.
Generalizable Information Theoretic Causal Representation
It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems.
Universality of parametric Coupling Flows over parametric diffeomorphisms
Invertible neural networks based on Coupling Flows CFlows) have various applications such as image synthesis and data compression.
Physics Constrained Flow Neural Network for Short-Timescale Predictions in Data Communications Networks
Machine learning is gaining growing momentum in various recent models for the dynamic analysis of information flows in data communications networks.
gCastle: A Python Toolbox for Causal Discovery
$\texttt{gCastle}$ is an end-to-end Python toolbox for causal structure learning.
Improving OOD Generalization with Causal Invariant Transformations
In this work, we obviate these assumptions and tackle the OOD problem without explicitly recovering the causal feature.
Informative Robust Causal Representation for Generalizable Deep Learning
In many real-world scenarios, such as image classification and recommender systems, it is evidence that representation learning can improve model's performance over multiple downstream tasks.
High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces.
Ranked #1 on
Molecular Graph Generation
on ZINC
Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on unseen target domains.
Ordering-Based Causal Discovery with Reinforcement Learning
It is a long-standing question to discover causal relations among a set of variables in many empirical sciences.
Understanding and Leveraging Causal Relations in Deep Reinforcement Learning
Reinforcement Learning (RL) has shown great potential to deal with sequential decision-making problems.
Causal World Models by Unsupervised Deconfounding of Physical Dynamics
The capability of imagining internally with a mental model of the world is vitally important for human cognition.
Weakly Supervised Disentangled Generative Causal Representation Learning
This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information.
Decoder-free Robustness Disentanglement without (Additional) Supervision
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features.
On Low Rank Directed Acyclic Graphs and Causal Structure Learning
Despite several advances in recent years, learning causal structures represented by directed acyclic graphs (DAGs) remains a challenging task in high dimensional settings when the graphs to be learned are not sparse.
A Causal Direction Test for Heterogeneous Populations
Our simulation result show that the proposed adjustment significantly improves the performance of the causal direction test statistic for heterogeneous data.
CausalVAE: Structured Causal Disentanglement in Variational Autoencoder
Learning disentanglement aims at finding a low dimensional representation which consists of multiple explanatory and generative factors of the observational data.
A Graph Autoencoder Approach to Causal Structure Learning
Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees.
Masked Gradient-Based Causal Structure Learning
This paper studies the problem of learning causal structures from observational data.
DO-AutoEncoder: Learning and Intervening Bivariate Causal Mechanisms in Images
Our experiments demonstrate our method is able to correctly identify the bivariate causal relationship between concepts in images and the representation learned enables a do-calculus manipulation to images, which generates artificial images that might possibly break the physical law depending on where we intervene the causal system.
Causal Discovery by Kernel Intrinsic Invariance Measure
We show our algorithm can be reduced to an eigen-decomposition task on a kernel matrix measuring intrinsic deviance/invariance.
Asymptotically Optimal One- and Two-Sample Testing with Kernels
With Sanov's theorem, we derive a sufficient condition for one-sample tests to achieve the optimal error exponent in the universal setting, i. e., for any distribution defining the alternative hypothesis.
Domain Generalization via Multidomain Discriminant Analysis
Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains.
Causal Discovery with Reinforcement Learning
The reward incorporates both the predefined score function and two penalty terms for enforcing acyclicity.
Kernel-based Multi-Task Contextual Bandits in Cellular Network Configuration
We evaluate the effectiveness of our algorithm based on a simulator built by real traces.
Causal Inference and Mechanism Clustering of A Mixture of Additive Noise Models
The inference of the causal relationship between a pair of observed variables is a fundamental problem in science, and most existing approaches are based on one single causal model.
A Kernel Embedding-based Approach for Nonstationary Causal Model Inference
Although nonstationary data are more common in the real world, most existing causal discovery methods do not take nonstationarity into consideration.
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning
Exogenous state variables and rewards can slow down reinforcement learning by injecting uncontrolled variation into the reward signal.
Exponentially Consistent Kernel Two-Sample Tests
Given two sets of independent samples from unknown distributions $P$ and $Q$, a two-sample test decides whether to reject the null hypothesis that $P=Q$.
Universal Hypothesis Testing with Kernels: Asymptotically Optimal Tests for Goodness of Fit
We show that two classes of Maximum Mean Discrepancy (MMD) based tests attain this optimality on $\mathbb R^d$, while the quadratic-time Kernel Stein Discrepancy (KSD) based tests achieve the maximum exponential decay rate under a relaxed level constraint.
Causal discovery with scale-mixture model for spatiotemporal variance dependencies
In conventional causal discovery, structural equation models (SEM) are directly applied to the observed variables, meaning that the causal effect can be represented as a function of the direct causes themselves.
