376 citations · 1.1k across the 17 of their papers we have counts for
6 papers · 1 filter
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
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 lear…
Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning
William Agnew, Pedro Domingos
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provid…
Deep Learning as a Mixed Convex-Combinatorial Optimization Problem
Abram L. Friesen, Pedro Domingos
As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically…
The Sum-Product Theorem: A Foundation for Learning Tractable Models
Abram L. Friesen, Pedro Domingos
Inference in expressive probabilistic models is generally intractable, which makes them difficult to learn and limits their applicability. Sum-product networks are a class of deep…
Exchangeable Variable Models
Mathias Niepert, Pedro Domingos
A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations. We introduce exchangeable variable models (EVMs) as a novel class…
Sum-Product Networks: A New Deep Architecture
Hoifung Poon, Pedro Domingos
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are general conditions under which the…