Search Results for author: Pedro Domingos

Found 15 papers, 3 papers with code

Every Model Learned by Gradient Descent Is Approximately a Kernel Machine

no code implementations30 Nov 2020 Pedro Domingos

Deep learning's successes are often attributed to its ability to automatically discover new representations of the data, rather than relying on handcrafted features like other learning methods.

Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity

1 code implementation28 Sep 2020 William Agnew, Christopher Xie, Aaron Walsman, Octavian Murad, Caelen Wang, Pedro Domingos, Siddhartha Srinivasa

By using these priors over the physical properties of objects, our system improves reconstruction quality not just by standard visual metrics, but also performance of model-based control on a variety of robotics manipulation tasks in challenging, cluttered environments.

3D Object Reconstruction 3D Reconstruction +1

Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning

no code implementations3 Mar 2020 William Agnew, Pedro Domingos

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency.

Atari Games Object +4

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

no code implementations10 Nov 2017 Tarek R. Besold, Artur d'Avila Garcez, Sebastian Bader, Howard Bowman, Pedro Domingos, Pascal Hitzler, Kai-Uwe Kuehnberger, Luis C. Lamb, Daniel Lowd, Priscila Machado Vieira Lima, Leo de Penning, Gadi Pinkas, Hoifung Poon, Gerson Zaverucha

Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation.


Deep Learning as a Mixed Convex-Combinatorial Optimization Problem

1 code implementation ICLR 2018 Abram L. Friesen, Pedro Domingos

Based on this, we develop a recursive mini-batch algorithm for learning deep hard-threshold networks that includes the popular but poorly justified straight-through estimator as a special case.

Combinatorial Optimization Quantization

The Sum-Product Theorem: A Foundation for Learning Tractable Models

no code implementations11 Nov 2016 Abram L. Friesen, Pedro Domingos

We illustrate the power and generality of this approach by applying it to a new type of structured prediction problem: learning a nonconvex function that can be globally optimized in polynomial time.

Structured Prediction

Recursive Decomposition for Nonconvex Optimization

no code implementations8 Nov 2016 Abram L. Friesen, Pedro Domingos

Similarly to DPLL-style SAT solvers and recursive conditioning in probabilistic inference, our algorithm, RDIS, recursively sets variables so as to simplify and decompose the objective function into approximately independent sub-functions, until the remaining functions are simple enough to be optimized by standard techniques like gradient descent.

Combinatorial Optimization graph partitioning +2

On the Latent Variable Interpretation in Sum-Product Networks

no code implementations22 Jan 2016 Robert Peharz, Robert Gens, Franz Pernkopf, Pedro Domingos

We discuss conditional independencies in augmented SPNs, formally establish the probabilistic interpretation of the sum-weights and give an interpretation of augmented SPNs as Bayesian networks.

Learning Tractable Probabilistic Models for Fault Localization

no code implementations7 Jul 2015 Aniruddh Nath, Pedro Domingos

While most previous statistical debugging methods generalize over many executions of a single program, TFLMs are trained on a corpus of previously seen buggy programs, and learn to identify recurring patterns of bugs.

Fault localization

Exchangeable Variable Models

no code implementations2 May 2014 Mathias Niepert, Pedro Domingos

A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations.

Structured Message Passing

no code implementations26 Sep 2013 Vibhav Gogate, Pedro Domingos

In this paper, we present structured message passing (SMP), a unifying framework for approximate inference algorithms that take advantage of structured representations such as algebraic decision diagrams and sparse hash tables.

Sum-Product Networks: A New Deep Architecture

1 code implementation14 Feb 2012 Hoifung Poon, Pedro Domingos

Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks.

Learning Efficient Markov Networks

no code implementations NeurIPS 2010 Vibhav Gogate, William Webb, Pedro Domingos

We present an algorithm for learning high-treewidth Markov networks where inference is still tractable.


Approximate Inference by Compilation to Arithmetic Circuits

no code implementations NeurIPS 2010 Daniel Lowd, Pedro Domingos

Arithmetic circuits (ACs) exploit context-specific independence and determinism to allow exact inference even in networks with high treewidth.

Variational Inference

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