TherML: Thermodynamics of Machine Learning

Name: TherML: Thermodynamics of Machine Learning
Author: Alexander A. Alemi, Ian Fischer

Alexander A. Alemi, Ian Fischer

paper2018-07-11English

Start Reading

machine learning financearxiv

Description

In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.

Similar Books

paper

Quantitative mode stability for the wave equation on the Kerr-Newman spacetime

Damon Civin

Quantitative mode stability for the wave equation on the Kerr-Newman spacetime

paper

Risk-Aware Objective-Based Forecasting in Inertia Management

Haipeng Zhang, Ran Li, Yan Chen, Zhongda Chu, Mingyang Sun

Risk-Aware Objective-Based Forecasting in Inertia Management

paper

Chainalysis: Geography of Cryptocurrency 2023

Chainalysis

Chainalysis: Geography of Cryptocurrency 2023

paper

Periodicity in Cryptocurrency Volatility and Liquidity

Peter Reinhard Hansen, Chan Kim, Wade Kimbrough

Periodicity in Cryptocurrency Volatility and Liquidity

paper

Impact of Geometric Uncertainty on the Computation of Abdominal Aortic Aneurysm Wall Strain

Saeideh Sekhavat, Mostafa Jamshidian, Adam Wittek, Karol Miller

Impact of Geometric Uncertainty on the Computation of Abdominal Aortic Aneurysm Wall Strain

paper

Simulation-based Bayesian inference with ameliorative learned summary statistics -- Part I

Getachew K. Befekadu

Simulation-based Bayesian inference with ameliorative learned summary statistics -- Part I