Methods › Sequential › Time Series Modules › Temporal Distribution Characterization
Temporal Distribution Characterization
Introduced by Yuntao Du et al. in AdaRNN: Adaptive Learning and Forecasting of Time Series
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Temporal Distribution Characterization, or TDC, is a module used in the AdaRNN architecture to characterize the distributional information in a time series.
Based on the principle of maximum entropy, maximizing the utilization of shared knowledge underlying a times series under temporal covariate shift can be done by finding periods which are most dissimilar to each other, which is also considered as the worst case of temporal covariate shift since the cross-period distributions are the most diverse. TDC achieves this goal for splitting the time-series by solving an optimization problem whose objective can be formulated as:
max_(0<K ≤K₀) max_(n₁, ⋯, n_K) 1/K ∑_(1 ≤i ≠j ≤K) d(𝒟ᵢ, 𝒟ⱼ)
s.t. ∀i, Δ₁<|𝒟ᵢ|<Δ₂ ; ∑ᵢ|𝒟ᵢ|=n
where d is a distance metric, Δ₁ and Δ₂ are predefined parameters to avoid trivial solutions (e.g., very small values or very large values may fail to capture the distribution information), and K₀ is the hyperparameter to avoid over-splitting. The metric d(·, ·) above can be any distance function, e.g., Euclidean or Editing distance, or some distribution-based distance / divergence, like MMD [14] and KL-divergence.
The learning goal of the optimization problem (1) is to maximize the averaged period-wise distribution distances by searching K and the corresponding periods so that the distributions of each period are as diverse as possible and the learned prediction model has better a more generalization ability.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: temporal collection-distribution mechanism; a novel method that combines out-of-distribution detection with time series modeling for temporal financial sentiment analysis; LWM-Temporal; Temporal System; Temporal DynSHAP; Temporal Query (TQ); Cross Temporal Loss; temporal memory (β).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 1 tagged papers has a Syntology run on record
Page 1 of 1: paper 1 of 1, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
AdaRNN: Adaptive Learning and Forecasting of Time Series 10 Aug 2021 · 2 repositories · arXiv:2108.04443
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Activity Recognition | 1 |
| Financial Analysis | 1 |
| Human Activity Recognition | 1 |
| Time Series | 1 |
| Time Series Analysis | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections