English
Related papers

Related papers: Thermodynamics of classifiers

200 papers

From a recent geometric generalization of Thermodynamic Uncertainty Relations (TURs) we derive novel upper bounds on the nonlinear response of an observable of an arbitrary system undergoing a change of probabilistic state. Various…

Statistical Mechanics · Physics 2022-03-09 Gianmaria Falasco , Massimiliano Esposito , Jean-Charles Delvenne

Within an inherently classical perspective, there is always an unavoidable energy cost associated with the information deletion and this common lore is at the heart of the Landauer's conjecture that does not impose, per se, any relevant…

Quantum Physics · Physics 2025-07-15 Massimo Giovannini

Computations implemented on a physical system are fundamentally limited by the laws of physics. A prominent example for a physical law that bounds computations is the Landauer principle. According to this principle, erasing a bit of…

Statistical Mechanics · Physics 2021-03-17 Roi Holtzman , Geva Arwas , Oren Raz

Using the operational framework of completely positive, trace preserving operations and thermodynamic fluctuation relations, we derive a lower bound for the heat exchange in a Landauer erasure process on a quantum system. Our bound comes…

Quantum Physics · Physics 2015-02-11 John Goold , Mauro Paternostro , Kavan Modi

We consider the additional entropy production (EP) incurred by a fixed quantum or classical process on some initial state $\rho$, above the minimum EP incurred by the same process on any initial state. We show that this additional EP, which…

Quantum Physics · Physics 2022-11-22 Artemy Kolchinsky , David H. Wolpert

The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits,…

Information Theory · Computer Science 2026-01-01 Jianfeng Xu , Zeyan Li

We address the problem of energy-error tradeoff in the discrimination between two linear passive quantum optical devices with a single use. We provide an analytical derivation of the optimal strategy for beamsplitters and an iterative…

Quantum Physics · Physics 2015-05-27 Alessandro Bisio , Michele Dall'Arno , Giacomo Mauro D'Ariano

We review the trade-offs between speed, fluctuations, and thermodynamic cost involved with biological processes in nonequilibrium states, and discuss how optimal these processes are in light of the universal bound set by the thermodynamic…

Biological Physics · Physics 2022-02-28 Yonghyun Song , Changbong Hyeon

The issue of discrete probability estimation for samples of small size is addressed in this study. The maximum likelihood method often suffers over-fitting when insufficient data is available. Although the Bayesian approach can avoid…

Machine Learning · Computer Science 2012-12-13 Takashi Isozaki

Developing a thermodynamic theory of computation is a challenging task at the interface of non-equilibrium thermodynamics and computer science. In particular, this task requires dealing with difficulties such as stochastic halting times,…

Statistical Mechanics · Physics 2024-05-14 Gonzalo Manzano , Gülce Kardeş , Édgar Roldán , David Wolpert

Information theoretic active learning has been widely studied for probabilistic models. For simple regression an optimal myopic policy is easily tractable. However, for other tasks and with more complex models, such as classification with…

Machine Learning · Statistics 2011-12-30 Neil Houlsby , Ferenc Huszár , Zoubin Ghahramani , Máté Lengyel

We present a thermodynamic analysis of a quantum engine that uses a single quantum particle as its working fluid, inspired by Szilard's classical single-particle engine. Our design is modeled after the classically-chaotic Szilard Map and…

Quantum Physics · Physics 2023-05-11 Srinivasa Rao. P

We derive an expression for the equilibrium probability distribution of a quantum state in contact with a noisy thermal environment that formally separates contributions from quantum and classical forms of probabilistic uncertainty. A…

Quantum Physics · Physics 2024-10-10 Henrik J. Heelweg , Amro Dodin , Adam P. Willard

Despite its simplicity, it seems to my best of knowledge that the possibly simplest approach towards deriving equations governing irreversible thermodynamics from gas-kinetic considerations within the framework of classical mechanics has…

Classical Physics · Physics 2016-08-22 Rudolf A. Hanel

We study a two-level system controlled in a discrete feedback loop, modeling both the system and the controller in terms of stochastic Markov processes. We find that the extracted work, which is known to be bounded from above by the mutual…

Statistical Mechanics · Physics 2015-09-02 Jaegon Um , Haye Hinrichsen , Chulan Kwon , Hyunggyu Park

We study the informational underpinnings of thermodynamics and statistical mechanics, using an abstract framework, general probabilistic theories, capable of describing arbitrary physical theories. This allows one to abstract the…

Quantum Physics · Physics 2019-01-25 Carlo Maria Scandolo

Landauer argued that the process of erasing the information stored in a memory device incurs an energy cost in the form of a minimum amount of mechanical work. We find, however, that this energy cost can be reduced to zero by paying a cost…

Quantum Physics · Physics 2011-06-02 Joan A. Vaccaro , Stephen M. Barnett

We initiate the systematic study of the energy complexity of algorithms (in addition to time and space complexity) based on Landauer's Principle in physics, which gives a lower bound on the amount of energy a system must dissipate if it…

Data Structures and Algorithms · Computer Science 2016-05-30 Erik D. Demaine , Jayson Lynch , Geronimo J. Mirano , Nirvan Tyagi

A perfectly rational decision-maker chooses the best action with the highest utility gain from a set of possible actions. The optimality principles that describe such decision processes do not take into account the computational costs of…

Artificial Intelligence · Computer Science 2013-12-25 Jordi Grau-Moya , Daniel A. Braun

Physical systems are often simulated using a stochastic computation where different final states result from identical initial states. Here, we derive the minimum energy cost of simulating a complex data set of a general physical system…

Data Analysis, Statistics and Probability · Physics 2015-05-30 Karoline Wiesner , Mile Gu , Elisabeth Rieper , Vlatko Vedral