中文
相关论文

相关论文: InvertibleNetworks.jl: A Julia package for scalabl…

200 篇论文

Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten invertible architectures and related models fare on two intuitive,…

机器学习 · 计算机科学 2021-06-23 Jakob Kruse , Lynton Ardizzone , Carsten Rother , Ullrich Köthe

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

机器学习 · 计算机科学 2021-08-06 Dmitry Baranchuk , Vladimir Aliev , Artem Babenko

The Normalizing Flow (NF) models a general probability density by estimating an invertible transformation applied on samples drawn from a known distribution. We introduce a new type of NF, called Deep Diffeomorphic Normalizing Flow (DDNF).…

机器学习 · 统计学 2018-11-26 Hadi Salman , Payman Yadollahpour , Tom Fletcher , Kayhan Batmanghelich

Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately, current approaches are only available for the most basic geometries and fall short when the underlying…

机器学习 · 统计学 2021-05-03 Luca Falorsi

Compilers are indispensable for transforming code written in high-level languages into performant machine code, but their general-purpose optimizations sometimes fall short. Domain experts might be aware of certain optimizations that the…

编程语言 · 计算机科学 2025-07-15 Jules Merckx , Tim Besard , Bjorn De Sutter

Normalizing flows are an essential alternative to GANs for generative modelling, which can be optimized directly on the maximum likelihood of the dataset. They also allow computation of the exact latent vector corresponding to an image…

机器学习 · 计算机科学 2021-08-10 Sandeep Nagar , Marius Dufraisse , Girish Varma

In this paper, we introduce the solver ConvexFlows for the convex flow problem first defined in the authors' previous work. In this problem, we aim to optimize a concave utility function depending on the flows over a graph. However, unlike…

最优化与控制 · 数学 2024-08-21 Theo Diamandis , Guillermo Angeris

Structural identifiability analysis determines whether the parameters of a mechanistic ordinary differential equation (ODE) model can be uniquely recovered from ideal observations and is therefore a fundamental prerequisite for reliable…

统计方法学 · 统计学 2026-05-20 Abdallah Alsammani

The notion of complex systems is common to many domains, from Biology to Economy, Computer Science, Physics, etc. Often, these systems are made of sets of entities moving in an evolving environment. One of their major characteristics is the…

数学软件 · 计算机科学 2008-12-18 Yoann Pigné , Antoine Dutot , Frédéric Guinand , Damien Olivier

We propose a novel perspective on varied-density clustering for high-dimensional data by framing it as a label propagation process in neighborhood graphs that adapt to local density variations. Our method formally connects density-based…

机器学习 · 计算机科学 2025-08-06 Ninh Pham , Yingtao Zheng , Hugo Phibbs

Normalizing flows attempt to model an arbitrary probability distribution through a set of invertible mappings. These transformations are required to achieve a tractable Jacobian determinant that can be used in high-dimensional scenarios.…

机器学习 · 统计学 2020-04-14 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

We introduce JPC, a JAX library for training neural networks with Predictive Coding. JPC provides a simple, fast and flexible interface to train a variety of PC networks (PCNs) including discriminative, generative and hybrid models. Unlike…

We present \texttt{MathOptAI.jl}, an open-source Julia library for embedding trained machine learning predictors into a JuMP model. \texttt{MathOptAI.jl} can embed a wide variety of neural networks, decision trees, and Gaussian Processes…

机器学习 · 计算机科学 2026-05-26 Oscar Dowson , Robert B Parker , Russel Bent

Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain…

机器学习 · 计算机科学 2019-12-24 Aditya Grover , Christopher Chute , Rui Shu , Zhangjie Cao , Stefano Ermon

IDEAL (Influence Diagram Evaluation and Analysis in Lisp) is a software environment for creation and evaluation of belief networks and influence diagrams. IDEAL is primarily a research tool and provides an implementation of many of the…

人工智能 · 计算机科学 2013-04-05 Sampath Srinivas , John S. Breese

N-body simulations and trajectory analysis rely on the calculation of attributes that depend on pairwise particle distances within a cutoff. Interparticle potential energies, forces, distribution functions, neighbor lists, and…

计算物理 · 物理学 2022-06-22 Leandro Martínez

Nonlinear optimization problems are found at the heart of real-time operations of critical infrastructures. These problems are computationally challenging because they embed complex physical models that exhibit space-time dynamics. We…

最优化与控制 · 数学 2026-05-11 Sungho Shin , Carleton Coffrin , Kaarthik Sundar , Victor M. Zavala

JuMP is an open-source modeling language that allows users to express a wide range of optimization problems (linear, mixed-integer, quadratic, conic-quadratic, semidefinite, and nonlinear) in a high-level, algebraic syntax. JuMP takes…

最优化与控制 · 数学 2017-05-08 Iain Dunning , Joey Huchette , Miles Lubin

We propose an expert-elicitation method for learning non-parametric joint prior distributions using normalizing flows. Normalizing flows are a class of generative models that enable exact, single-step density evaluation and can capture…

统计方法学 · 统计学 2025-04-22 Florence Bockting , Stefan T. Radev , Paul-Christian Bürkner

Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one. Based on iterative Gaussianization, we propose a new type of normalizing flow model that enables both…

机器学习 · 计算机科学 2020-03-05 Chenlin Meng , Yang Song , Jiaming Song , Stefano Ermon
‹ 上一页 1 8 9 10 下一页 ›