Autocorrelation is a defining characteristic of time-series data, where each observation is statistically dependent on its predecessors. In the context of deep time-series forecasting, autocorrelation arises in both the input history and the label sequences, presenting two central research challenges: (1) designing neural architectures that model autocorrelation in history sequences, and (2) devising learning objectives that model autocorrelation in label sequences. Recent studies have made strides in tackling these challenges, but a systematic survey examining both aspects remains lacking. To bridge this gap, this paper provides a comprehensive review of deep time-series forecasting from the perspective of autocorrelation modeling. In contrast to existing surveys, this work makes two distinctive contributions. First, it proposes a novel taxonomy that encompasses recent literature on both model architectures and learning objectives -- whereas prior surveys neglect or inadequately discuss the latter aspect. Second, it offers a thorough analysis of the motivations, insights, and progression of the surveyed literature from a unified, autocorrelation-centric perspective, providing a holistic overview of the evolution of deep time-series forecasting. The full list of papers and resources is available at https://github.com/Master-PLC/Awesome-TSF-Papers.

Fortheformer setting, an extensive literature has explored the statistical and computational aspects of learning Booleanfunctions[Angluin,1992,HellersteinandServedio,2007].

Dayan's SR [3] is well-suited for transfer learning in settings with fixed dynamics, as the decomposition ofthevaluefunction intorepresentations ofexpected outcomes (future stateoccupancies) andcorresponding rewards allowsustoquickly recompute values under newrewardsettings.

Under the new analysis, to achieve an -stationary point of the nested problem, it requiresO( 2)samples in total.

We will add these additional results to the paper. Reviewer mentioned that "the effect of the random initialization23 andshuffling(RIS)inthealgorithm isnotclear".

In particular, they tend to be overconfident.

This scaling behavior coincides with the one reportedinTripuranenietal. (2020)usingGaussiancomplexity.

We first discuss the broader impact of the proposed DynamicD inSec. D presents the training dynamics for the further analysis. E also conducts qualitative experiments to verify whether our approach memorizes the real images for extremely limited data. F shows the hyper-parameter analysis. It demonstrates the importance of discriminator in the two-player competition as simply adjusting the capacity could lead tosuch significant improvements on avarietyof settings, making training generative models more accessible to everyone.

Themostpopular fashion of SSFSL is to predict unlabeled data with pseudo-labels by carefully devising tailored strategies, and then augment the extremely small support set of labeled data in few-shot classification,e.g., [9,15,36].

While mode collapse is typically a side effect for generative modeling, it is somewhat "welcomed" in SoTA image captioning models as it usually facilitates a higher evaluation performance on reference-based metrics like CIDEr, BLEU and SPICE.