The paper develops a martingale-consistent SSL framework enforcing expected coherence between coarse and refined predictions via new objectives and a Monte Carlo estimator, improving robustness under partial observations.
Ti-mae: Self-supervised masked time series autoencoders
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 7verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
Masked autoencoder pretraining on 3.5 million timesteps of real drilling telemetry reduces total mud volume prediction error by 19.8% versus supervised GRU but trails LSTM by 6.4% on Utah FORGE wells.
Dynamics-centric mixtures of local reconstruction, temporal continuity, and in-context dynamics objectives in PathoFM yield the most balanced transfer across tasks and subjects on clinical gait time series.
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.
Affine mapping dominates LTSF benchmarks by learning similar input-to-output transition matrices, captures periodic signals well but struggles with non-periodic or cross-channel varying periods; reversible normalization converts trends to periodic-like patterns.
A literature review of thirteen papers finds that masked autoencoders have not been applied to downhole metric prediction from surface drilling data despite their advantages for unlabeled time-series modeling.
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.
citing papers explorer
-
Martingale-Consistent Self-Supervised Learning
The paper develops a martingale-consistent SSL framework enforcing expected coherence between coarse and refined predictions via new objectives and a Monte Carlo estimator, improving robustness under partial observations.
-
Do Masked Autoencoders Improve Downhole Prediction? An Empirical Study on Real Well Drilling Data
Masked autoencoder pretraining on 3.5 million timesteps of real drilling telemetry reduces total mud volume prediction error by 19.8% versus supervised GRU but trails LSTM by 6.4% on Utah FORGE wells.
-
On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series
Dynamics-centric mixtures of local reconstruction, temporal continuity, and in-context dynamics objectives in PathoFM yield the most balanced transfer across tasks and subjects on clinical gait time series.
-
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.
-
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
Affine mapping dominates LTSF benchmarks by learning similar input-to-output transition matrices, captures periodic signals well but struggles with non-periodic or cross-channel varying periods; reversible normalization converts trends to periodic-like patterns.
-
Assessing the Potential of Masked Autoencoder Foundation Models in Predicting Downhole Metrics from Surface Drilling Data
A literature review of thirteen papers finds that masked autoencoders have not been applied to downhole metric prediction from surface drilling data despite their advantages for unlabeled time-series modeling.
-
Universal Time-Series Representation Learning: A Survey
A survey that proposes a taxonomy for universal time-series representation learning and reviews existing deep learning studies along with experimental setups.