Unifying AI Algorithms with Probabilistic Programming using Implicitly Defined Representations
We introduce Scruff, a new framework for developing AI systems using probabilistic programming. Scruff enables a variety of representations to be included, such as code with stochastic choices, neural networks, differential equations, and constraint systems. These representations are defined implicitly using a set of standardized operations that can be performed on them. General-purpose algorithms are then implemented using these operations, enabling generalization across different representations. Zero, one, or more operation implementations can be provided for any given representation, giving algorithms the flexibility to use the most appropriate available implementations for their purposes and enabling representations to be used in ways that suit their capabilities. In this paper, we explain the general approach of implicitly defined representations and provide a variety of examples of representations at varying degrees of abstraction. We also show how a relatively small set of operations can serve to unify a variety of AI algorithms. Finally, we discuss how algorithms can use policies to choose which operation implementations to use during execution.
Code (0)
등록된 구현이 없습니다.
Tasks
Probabilistic ProgrammingSimilar Papers 제목 키워드 기반
Probabilistic unifying relations for modelling epistemic and aleatoric uncertainty: semantics and automated reasoning with theorem proving
Probabilistic programming combines general computer programming, statistical inference, and formal semantics to help systems make decisions when facing uncertainty. Probabilistic programs are ubiquitous, including having…
Automated Theorem ProvingProbabilistic ProgrammingImprovements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators
We consider the problem of Bayesian inference in the family of probabilistic models implicitly defined by stochastic generative models of data. In scientific fields ranging from population biology to cosmology, low-level…
Bayesian InferenceProbabilistic ProgrammingNonparametric Involutive Markov Chain Monte Carlo
A challenging problem in probabilistic programming is to develop inference algorithms that work for arbitrary programs in a universal probabilistic programming language (PPL). We present the nonparametric involutive Mark…
Probabilistic ProgrammingFunctional Tensors for Probabilistic Programming
It is a significant challenge to design probabilistic programming systems that can accommodate a wide variety of inference strategies within a unified framework. Noting that the versatility of modern automatic differenti…
Probabilistic ProgrammingA Unifying View of Optimism in Episodic Reinforcement Learning
The principle of optimism in the face of uncertainty underpins many theoretically successful reinforcement learning algorithms. In this paper we provide a general framework for designing, analyzing and implementing such …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)