Search Results for author: Zhe Zeng

Found 11 papers, 6 papers with code

A Unified Approach to Count-Based Weakly-Supervised Learning

1 code implementation22 Nov 2023 Vinay Shukla, Zhe Zeng, Kareem Ahmed, Guy Van Den Broeck

In many cases, these weak labels dictate the frequency of each respective class over a set of instances.

Weakly-supervised Learning

Probabilistically Rewired Message-Passing Neural Networks

1 code implementation3 Oct 2023 Chendi Qian, Andrei Manolache, Kareem Ahmed, Zhe Zeng, Guy Van Den Broeck, Mathias Niepert, Christopher Morris

Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input.

Collapsed Inference for Bayesian Deep Learning

1 code implementation NeurIPS 2023 Zhe Zeng, Guy Van Den Broeck

We tackle this challenge by revealing a previously unseen connection between inference on BNNs and volume computation problems.

SIMPLE: A Gradient Estimator for $k$-Subset Sampling

1 code implementation4 Oct 2022 Kareem Ahmed, Zhe Zeng, Mathias Niepert, Guy Van Den Broeck

$k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity.

Tractable Computation of Expected Kernels

1 code implementation21 Feb 2021 Wenzhe Li, Zhe Zeng, Antonio Vergari, Guy Van Den Broeck

Computing the expectation of kernel functions is a ubiquitous task in machine learning, with applications from classical support vector machines to exploiting kernel embeddings of distributions in probabilistic modeling, statistical inference, causal discovery, and deep learning.

Causal Discovery

Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations

no code implementations NeurIPS 2020 Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari, Guy Van Den Broeck

Weighted model integration (WMI) is a framework to perform advanced probabilistic inference on hybrid domains, i. e., on distributions over mixed continuous-discrete random variables and in presence of complex logical and arithmetic constraints.

Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing

1 code implementation ICML 2020 Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari, Guy Van Den Broeck

Weighted model integration (WMI) is a very appealing framework for probabilistic inference: it allows to express the complex dependencies of real-world problems where variables are both continuous and discrete, via the language of Satisfiability Modulo Theories (SMT), as well as to compute probabilistic queries with complex logical and arithmetic constraints.

Hybrid Probabilistic Inference with Logical Constraints: Tractability and Message Passing

no code implementations20 Sep 2019 Zhe Zeng, Fanqi Yan, Paolo Morettin, Antonio Vergari, Guy Van Den Broeck

Weighted model integration (WMI) is a very appealing framework for probabilistic inference: it allows to express the complex dependencies of real-world hybrid scenarios where variables are heterogeneous in nature (both continuous and discrete) via the language of Satisfiability Modulo Theories (SMT); as well as computing probabilistic queries with arbitrarily complex logical constraints.

Efficient Search-Based Weighted Model Integration

no code implementations13 Mar 2019 Zhe Zeng, Guy Van Den Broeck

Weighted model integration (WMI) extends Weighted model counting (WMC) to the integration of functions over mixed discrete-continuous domains.

Computational Efficiency Probabilistic Programming

Stein Variational Message Passing for Continuous Graphical Models

no code implementations ICML 2018 Dilin Wang, Zhe Zeng, Qiang Liu

We propose a novel distributed inference algorithm for continuous graphical models, by extending Stein variational gradient descent (SVGD) to leverage the Markov dependency structure of the distribution of interest.

Cannot find the paper you are looking for? You can Submit a new open access paper.