paper-with-me

Papers

Automatic Differentiation via Effects and Handlers: An Implementation in Frank

2021-01-20 · Jesse Sigal

Automatic differentiation (AD) is an important family of algorithms which enables derivative based optimization. We show that AD can be simply implemented with effects and handlers by doing so in the Frank language. By considering how our implementation behaves in Frank's operational semantics, we show how our code performs the dynamic creation of programs during evaluation.

📄 PDF Abstract BibTeX arXiv:2101.08095

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

2019-12-24 · Du Phan, Neeraj Pradhan, Martin Jankowiak

NumPyro is a lightweight library that provides an alternate NumPy backend to the Pyro probabilistic programming language with the same modeling interface, language primitives and effect handling abstractions. Effect hand…

Probabilistic Programming

Effect Handling for Composable Program Transformations in Edward2

2018-11-15 · Dave Moore, Maria I. Gorinova

Algebraic effects and handlers have emerged in the programming languages community as a convenient, modular abstraction for controlling computational effects. They have found several applications including concurrent pro…

Probabilistic Programming

A Step-by-step Introduction to the Implementation of Automatic Differentiation

2024-02-25 · Yu-Hsueh Fang, He-Zhe Lin, Jie-Jyun Liu, Chih-Jen Lin

Automatic differentiation is a key component in deep learning. This topic is well studied and excellent surveys such as Baydin et al. (2018) have been available to clearly describe the basic concepts. Further, sophistica…

On Reinforcement Learning, Effect Handlers, and the State Monad

2022-03-29 · Ugo Dal Lago, Francesco Gavazzo, Alexis Ghyselen

We study the algebraic effects and handlers as a way to support decision-making abstractions in functional programs, whereas a user can ask a learning algorithm to resolve choices without implementing the underlying sele…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Differentiable All-pole Filters for Time-varying Audio Systems

2024-04-11 · Chin-Yun Yu, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao 외

Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these system…

AllAudio Effects ModelingAudio Synthesis