paper-with-me

Papers

Aligning Time Series on Incomparable Spaces

2020-06-22 · Samuel Cohen, Giulia Luise, Alexander Terenin, Brandon Amos, Marc Peter Deisenroth

Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces. In this work, we consider a setting in which time series live on different spaces without a sensible ground metric, causing DTW to become ill-defined. To alleviate this, we propose Gromov dynamic time warping (GDTW), a distance between time series on potentially incomparable spaces that avoids the comparability requirement by instead considering intra-relational geometry. We demonstrate its effectiveness at aligning, combining and comparing time series living on incomparable spaces. We further propose a smoothed version of GDTW as a differentiable loss and assess its properties in a variety of settings, including barycentric averaging, generative modeling and imitation learning.

📄 PDF Abstract BibTeX arXiv:2006.12648

Code (1)

samcohen16/Aligning-Time-Series 공식 구현 pytorch

Tasks

Dynamic Time WarpingImitation LearningTime SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

DTW Dynamic Time Warping (DTW) [1] is one of well-known distance measures between a pairwise of time series. The main idea of DTW is to compute the distance from the matching of…

Similar Papers 제목 키워드 기반

A contribution to Optimal Transport on incomparable spaces

2020-11-09 · Titouan Vayer

Optimal Transport is a theory that allows to define geometrical notions of distance between probability distributions and to find correspondences, relationships, between sets of points. Many machine learning applications…

BIG-bench Machine LearningDomain Adaptation

Learning Generative Models across Incomparable Spaces

2019-05-14 · Charlotte Bunne, David Alvarez-Melis, Andreas Krause, Stefanie Jegelka

Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (…

Relational Reasoning

Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces

2024-07-20 · Athina Sotiropoulou, David Alvarez-Melis

Optimal Transport (OT) has recently emerged as a powerful framework for learning minimal-displacement maps between distributions. The predominant approach involves a neural parametrization of the Monge formulation of OT,…

LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting

2024-11-24 · Lingzheng Zhang, Lifeng Shen, Yimin Zheng, Shiyuan Piao 외

Recent research has shown that large language models (LLMs) can be effectively used for real-world time series forecasting due to their strong natural language understanding capabilities. However, aligning time series in…

Computational EfficiencyNatural Language UnderstandingTime SeriesTime Series Forecasting+1

Are All Good Word Vector Spaces Isomorphic?

2020-04-08 · EMNLP 2020 11 · Ivan Vulić, Sebastian Ruder, Anders Søgaard

Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on non-isomorphic spaces. Such non-isomorphism…

All