English
Related papers

Related papers: Erasure without work in an asymmetric, double-well…

200 papers

A coding scheme for write once memory (WOM) using polar codes is presented. It is shown that the scheme achieves the capacity region of noiseless WOMs when an arbitrary number of multiple writes is permitted. The encoding and decoding…

Information Theory · Computer Science 2012-10-09 David Burshtein , Alona Strugatski

We speculate whether the second law of thermodynamics has more to do with Turing machines than steam pipes. It states the logical reversibility of reality as a computation, i.e., the fact that no information is forgotten: nature computes…

Quantum Physics · Physics 2018-10-15 Stefan Wolf

The Landauer principle states that any logically irreversible information processing must be accompanied by dissipation into the environment. In this study, we investigate the heat dissipation associated with finite-time information erasure…

Statistical Mechanics · Physics 2022-01-05 Tan Van Vu , Keiji Saito

Lengthening a computer memory's lifespan is important for e-waste and sustainability. Uneven wear of memory is a major barrier. The problem is becoming even more urgent as emerging memory such as phase-change memory is subject to even…

Hardware Architecture · Computer Science 2026-01-29 Elizabeth Shen , Huiyang Zhou

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…

Machine Learning · Computer Science 2024-07-16 Mark He Huang , Lin Geng Foo , Jun Liu

We generalize stochastic thermodynamics to include information reservoirs. Such information reservoirs, which can be modeled as a sequence of bits, modify the second law. For example, work extraction from a system in contact with a single…

Statistical Mechanics · Physics 2014-11-17 Andre C. Barato , Udo Seifert

We investigate quantum channels, which after a finite number $k$ of repeated applications erase all input information, i.e., channels whose $k$-th power (but no smaller power) is a completely depolarizing channel. We show that on a system…

Quantum Physics · Physics 2012-05-04 Andre Ahlbrecht , Florian Richter , Reinhard F. Werner

Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize…

Machine Learning · Computer Science 2022-01-31 Yann Dubois , Benjamin Bloem-Reddy , Karen Ullrich , Chris J. Maddison

This study aims to quantify and visualize the degradation of fidelity (information degradation) that inevitably accompanies the replication of information within the framework of information thermodynamics and to propose an…

Mathematical Physics · Physics 2025-11-20 Tatsuaki Tsuruyama

We design a heat engine with multi-heat-reservoir, ancillary system and quantum memory. We then derive an inequality related with the second law of thermodynamics, and give a new limitation about the work gain from the engine by analyzing…

Quantum Physics · Physics 2017-11-09 Li-Hang Ren , Heng Fan

The Right to be Forgotten is a core principle outlined by regulatory frameworks such as the EU's General Data Protection Regulation (GDPR). This principle allows individuals to request that their personal data be deleted from deployed…

Machine Learning · Computer Science 2024-02-19 Alex Oesterling , Jiaqi Ma , Flavio P. Calmon , Hima Lakkaraju

Polar codes were introduced in 2009 and proven to achieve the symmetric capacity of any binary-input discrete memoryless channel under low-complexity successive cancellation decoding. In this thesis, we construct cyclic polar codes based on…

Information Theory · Computer Science 2020-04-16 Narayanan Rengaswamy

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Machine Learning · Computer Science 2021-06-22 Aditya Golatkar , Alessandro Achille , Avinash Ravichandran , Marzia Polito , Stefano Soatto

Fast polarization is crucial for the performance guarantees of polar codes. In the memoryless setting, the rate of polarization is known to be exponential in the square root of the block length. A complete characterization of the rate of…

Information Theory · Computer Science 2018-08-16 Boaz Shuval , Ido Tal

We investigate sublinear-time algorithms that take partially erased graphs represented by adjacency lists as input. Our algorithms make degree and neighbor queries to the input graph and work with a specified fraction of adversarial…

Data Structures and Algorithms · Computer Science 2020-12-01 Amit Levi , Ramesh Krishnan S. Pallavoor , Sofya Raskhodnikova , Nithin Varma

An algorithm of the tensor renormalization group is proposed based on a randomized algorithm for singular value decomposition. Our algorithm is applicable to a broad range of two-dimensional classical models. In the case of a square…

Statistical Mechanics · Physics 2018-03-23 Satoshi Morita , Ryo Igarashi , Hui-Hai Zhao , Naoki Kawashima

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

We develop a thermodynamic theory of algorithmic catalysis within the watts-per-intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration…

Information Theory · Computer Science 2026-04-24 Elija Perrier

In a recent paper [Vaikuntanathan and Jarzynski, Phys. Rev. E {\bf 83}, 061120 (2011), arXiv:1105.1744] a model was introduced whereby work could be extracted from a thermal bath by measuring the energy of a particle that was thermalized by…

Statistical Mechanics · Physics 2015-06-17 Joakim Bergli

Erasure is fundamental for information processing. It is also key in connecting information theory and thermodynamics, as it is a logically irreversible task. We provide a new angle on this connection, noting that there may be an additional…

Quantum Physics · Physics 2022-11-30 Maria Violaris , Chiara Marletto