English
Related papers

Related papers: Decomposing reverse-mode automatic differentiation

200 papers

Reciprocal transformations mix the role of the dependent and independent variables to achieve simpler versions or even linearized versions of nonlinear PDEs. These transformations help in the identification of a plethora of PDEs available…

Mathematical Physics · Physics 2016-04-08 C. Sardon

This paper presents the forward and backward derivatives of partial eigendecomposition, i.e. where it only obtains some of the eigenpairs, of a real symmetric matrix for degenerate cases. The numerical calculation of forward and backward…

Numerical Analysis · Mathematics 2020-11-10 Muhammad Firmansyah Kasim

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular it has recently been demonstrated, using the artificial intelligence algorithm…

Emerging Technologies · Computer Science 2018-02-09 Michiel Hermans , Piotr Antonik , Marc Haelterman , Serge Massar

Foundation models, such as large language models, have demonstrated success in addressing various language and image processing tasks. In this work, we introduce a multi-modal foundation model for scientific problems, named PROSE-PDE. Our…

Machine Learning · Computer Science 2025-02-04 Jingmin Sun , Yuxuan Liu , Zecheng Zhang , Hayden Schaeffer

Dynamic mode decomposition (DMD) is a versatile approach that enables the construction of low-order models from data. Controller design tasks based on such models require estimates and guarantees on predictive accuracy. In this work, we…

Systems and Control · Electrical Eng. & Systems 2020-03-24 Qiugang Lu , Sungho Shin , Victor M. Zavala

The synthesis of string transformation programs from input-output examples utilizes various techniques, all based on an inductive bias that comprises a restricted set of basic operators to be combined. A new algorithm, Transduce, is…

Machine Learning · Computer Science 2024-01-19 Francis Frydman , Philippe Mangion

To reversify an arbitrary sequential algorithm $A$, we gently instrument $A$ with bookkeeping machinery. The result is a step-for-step reversible algorithm that mimics $A$ step-for-step and stops exactly when $A$ does. Without loss of…

Quantum Physics · Physics 2021-06-29 Yuri Gurevich

We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the…

Machine Learning · Statistics 2019-06-13 Emile Mathieu , Tom Rainforth , N. Siddharth , Yee Whye Teh

Differentiation along algorithms, i.e., piggyback propagation of derivatives, is now routinely used to differentiate iterative solvers in differentiable programming. Asymptotics is well understood for many smooth problems but the…

Optimization and Control · Mathematics 2022-06-02 Jérôme Bolte , Edouard Pauwels , Samuel Vaiter

A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we develop an approach that improves…

Machine Learning · Computer Science 2024-02-13 Yi-Lin Tuan , Zih-Yun Chiu , William Yang Wang

As Vision-Language Models (VLMs) become increasingly sophisticated and widely used, it becomes more and more crucial to understand their decision-making process. Traditional explainability methods, designed for classification tasks,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Walid Bousselham , Angie Boggust , Hendrik Strobelt , Hilde Kuehne

Deep neural networks employing error back-propagation for learning can suffer from exploding and vanishing gradient problems. Numerous solutions have been proposed such as normalisation techniques or limiting activation functions to linear…

Machine Learning · Computer Science 2023-09-08 Sama Daryanavard , Bernd Porr

A novel permutation decoding method for Reed-Muller codes is presented. The complexity and the error correction performance of the suggested permutation decoding approach are similar to that of the recursive lists decoder. It is…

Information Theory · Computer Science 2019-10-28 Mikhail Kamenev , Yulia Kameneva , Oleg Kurmaev , Alexey Maevskiy

Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize…

Machine Learning · Computer Science 2018-12-13 Michael Tschannen , Olivier Bachem , Mario Lucic

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine…

Computation and Language · Computer Science 2024-10-18 Chengpeng Fu , Xiaocheng Feng , Yichong Huang , Wenshuai Huo , Baohang Li , Hui Wang , Bin Qin , Ting Liu

Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own activations. We introduce Universal Activation Verbalizer…

Computation and Language · Computer Science 2026-05-26 Haiyan Zhao , Zirui He , Guanchu Wang , Ali Payani , Yingcong Li , Mengnan Du

The development of mode-division multiplexing techniques is an important step to increase the information processing capacity. In this context, we design an efficient and robust mode-division (de)multiplexing integrated device based on the…

Optics · Physics 2018-06-04 G. Queraltó , V. Ahufinger , J. Mompart

Parallel decoding for diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneously requires accounting for inter-token dependencies. We…

Machine Learning · Computer Science 2026-03-16 Bumjun Kim , Dongjae Jeon , Moongyu Jeon , Albert No

Mechanistic interpretability aims to understand the internal mechanisms learned by neural networks. Despite recent progress toward this goal, it remains unclear how best to decompose neural network parameters into mechanistic components. We…

Machine Learning · Computer Science 2025-02-11 Dan Braun , Lucius Bushnaq , Stefan Heimersheim , Jake Mendel , Lee Sharkey

We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…

Machine Learning · Computer Science 2021-10-28 Sriram Ravula , Georgios Smyrnis , Matt Jordan , Alexandros G. Dimakis
‹ Prev 1 8 9 10 Next ›