对于不规则时间序列的异构时态变量自编码器
Satya Narayan Shukla1, Benjamin M Marlin1
1College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA 01003, USA.
... International Conference on Learning Representations
|February 25, 2026
概括
我们介绍了 Heteroscedastic Temporal Variational Autoencoder (HeTVAE),这是一个深度学习框架,用于插入不规则样本的时间序列. HeTVAE有效地建模并反映由稀疏数据引起的时间不确定性.
科学领域:
- 机器学习 机器学习
- 时间序列分析时间序列分析
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 不定期采样的时间序列对标准深度学习模型构成挑战.
- 精确的插值和不确定性量化在数据稀疏的领域中至关重要.
研究的目的:
- 开发一种新的深度学习框架,用于不规则采样时间序列的概率插值.
- 改进时间序列数据中的不确定性建模,采用不规则的抽样模式.
主要方法:
- 提出了异构时态变量自编码器 (HeTVAE) 框架.
- 引入了一个新的输入层来编码观测稀疏性.
- 使用时间变异自编码器 (VAE) 架构来传播不确定性.
- 整合了一个异构的输出层,用于插入的变量不确定性.
主要成果:
- 与基线和传统模型相比,HeTVAE在反映随时间变量的不确定性方面表现出卓越的表现.
- 拟议的架构性能优于最近的深潜变量模型,具有同源的输出层.
- HeTVAE有效地处理了因稀疏和不规则的时间序列抽样而产生的不确定性.
结论:
- 异时间变量自编码器 (HeTVAE) 提供了一个有效的解决方案,用于不规则采样时间序列的概率插值.
- 在稀疏数据场景中,HeTVAE模拟异种不确定性的能力是其在稀疏数据场景中性能改善的关键.
- 这一框架为处理真实世界,不规则采样的时间数据的深度学习应用提供了显著的进步.
相关概念视频
01:21Linear Approximation in Time Domain
384
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
384
01:11Sampling Continuous Time Signal
783
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
783
01:23Curvilinear Motion: Rectangular Components
1.4K
Curvilinear motion characterizes the movement of a particle or object along a curved path, notably evident when envisioning a car navigating a winding road. If the car starts at point A, its position vector is established within a fixed frame of reference, where the ratio of the position vector to its magnitude signifies the unit vector pointing in the position vector's direction.
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
1.4K
01:23Linear time-invariant Systems
993
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
993
01:26Linear Approximation in Frequency Domain
407
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
407
01:22Basic Continuous Time Signals
742
Basic continuous-time signals include the unit step function, unit impulse function, and unit ramp function, collectively referred to as singularity functions. Singularity functions are characterized by discontinuities or discontinuous derivatives.
The unit step function, denoted u(t), is zero for negative time values and one for positive time values, exhibiting a discontinuity at t=0. This function often represents abrupt changes, such as the step voltage introduced when turning a car's...
The unit step function, denoted u(t), is zero for negative time values and one for positive time values, exhibiting a discontinuity at t=0. This function often represents abrupt changes, such as the step voltage introduced when turning a car's...
742