Liquid structural state-space models

R Hasani, M Lechner, TH Wang, M Chahine… - arxiv preprint arxiv …, 2022 - arxiv.org
A proper parametrization of state transition matrices of linear state-space models (SSMs)
followed by standard nonlinearities enables them to efficiently learn representations from …

Learning long-term dependencies in irregularly-sampled time series

M Lechner, R Hasani - arxiv preprint arxiv:2006.04418, 2020 - arxiv.org
Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for
modeling irregularly-sampled time series. These models, however, face difficulties when the …

Automated enforcement of SLA for cloud services

S Vakilinia, C Truchan, J Kempf… - 2018 IEEE 11th …, 2018 - ieeexplore.ieee.org
Orchestration and management of cloud computing entities necessitate measuring and
analysis of real-time monitored performance metrics. However, decision making in current …

OpenStack network acceleration scheme for datacenter intelligent applications

L Phan, K Liu - 2018 IEEE 11th International Conference on …, 2018 - ieeexplore.ieee.org
Cloud virtualization and multi-tenant networking provide Infrastructure as a Service (IaaS)
providers a new and innovative way to offer on-demand services to their customers, such as …

Mixed-memory rnns for learning long-term dependencies in irregularly sampled time series

M Lechner, R Hasani - 2022 - openreview.net
Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for
modeling irregularly sampled time series. These models, however, face difficulties when the …

On the applicability of the Lead/Lag Ratio in causality assessment

M Zanin, S Belkoura - Physica A: Statistical Mechanics and its Applications, 2018 - Elsevier
Within the large set of metrics that have been proposed to assess the presence of a causality
relationship between time series, the Lead/Lag Ratio (LLR) has recently attracted increasing …