Miguel Lázaro-Gredilla — accepted AI-conference papers

2023

3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation

Guangyao Zhou, Nishad Gothoskar, Lirui Wang, Joshua B. Tenenbaum, Dan Gutfreund, Miguel Lázaro-Gredilla +2

ICCV 2023poster

The ability to perceive and understand 3D scenes is crucial for many applications in computer vision and robotics. Inverse graphics is an appealing approach to 3D scene understanding that aims to infer the 3D scene structure from 2D images. In this paper, we introduce probabilistic modeling to the i…

Cited by 4 PDF ↗code ↗Scholar ↗

2021

Query Training: Learning a Worse Model to Infer Better Marginals in Undirected Graphical Models with Hidden Variables

Miguel Lázaro-Gredilla, Wolfgang Lehrach, Nishad Gothoskar, Guangyao Zhou, Antoine Dedieu, Dileep George

AAAI 2021technical

Probabilistic graphical models (PGMs) provide a compact representation of knowledge that can be queried in a flexible way: after learning the parameters of a graphical model once, new probabilistic queries can be answered at test time without retraining. However, when using undirected PGMS with hidd…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2021

Sample-Efficient L0-L2 Constrained Structure Learning of Sparse Ising Models

Antoine Dedieu, Miguel Lázaro-Gredilla, Dileep George

AAAI 2021technical

We consider the problem of learning the underlying graph of a sparse Ising model with p nodes from n i.i.d. samples. The most recent and best performing approaches combine an empirical loss (the logistic regression loss or the interaction screening loss) with a regularizer (an L1 penalty or an L1 co…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2017

Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics

Ken Kansky, Tom Silver, David A. Mély, Mohamed Eldawy, Miguel Lázaro-Gredilla, Xinghua Lou +4

ICML 2017poster

The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress on task-to-task transfer remains limited. In pursuit of efficient and robust generalization, we introduce the Schema Ne…

Cited by 300 Source ↗PDF ↗Scholar ↗

2015

Local Expectation Gradients for Black Box Variational Inference

Michalis Titsias RC AUEB, Miguel Lázaro-Gredilla

NeurIPS 2015poster

We introduce local expectation gradients which is a general purpose stochastic variational inference algorithm for constructing stochastic gradients by sampling from the variational distribution. This algorithm divides the problem of estimating the stochastic gradients over multiple variational para…

Cited by 101 Source ↗PDF ↗Scholar ↗