We study decentralized optimization over a network of agents, modeled as an undirected graph and operating without a central server. The objective is to minimize a composite function $f+r$, where $f$ is a (strongly) convex function representing the average of the agents' losses, and $r$ is a convex, extended-value function (regularizer). We introduce DCatalyst, a unified black-box framework that injects Nesterov-type acceleration into decentralized optimization algorithms. At its core, DCatalyst is an inexact, momentum-accelerated proximal scheme (outer loop) that seamlessly wraps around a given decentralized method (inner loop). We show that DCatalyst attains optimal (up to logarithmic factors) communication and computational complexity across a broad family of decentralized algorithms and problem instances. In particular, it delivers accelerated rates for problem classes that previously lacked accelerated decentralized methods, thereby broadening the effectiveness of decentralized methods. On the technical side, our framework introduces inexact estimating sequences--an extension of Nesterov's classical estimating sequences, tailored to decentralized, composite optimization. This construction systematically accommodates consensus errors and inexact solutions of local subproblems, addressing challenges that existing estimating-sequence-based analyses cannot handle while retaining a black-box, plug-and-play character.

In online video platforms, accurate watch time prediction has become a fundamental and challenging problem in video recommendation. Previous research has revealed that the accuracy of watch time prediction highly depends on both the transformation of watch-time labels and the decomposition of the estimation process. TPM (Tree based Progressive Regression Model) achieves State-of-the-Art performance with a carefully designed and effective decomposition paradigm. TPM discretizes the watch time into several ordinal intervals and organizes them into a binary decision tree, where each node corresponds to a specific interval. At each non-leaf node, a binary classifier is used to determine the specific interval in which the watch time variable most likely falls, based on the prediction outcome at its parent node.

An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems. To achieve this, there are four properties that a watch time prediction framework should satisfy: first, despite its continuous value, watch time is also an ordinal variable and the relative ordering between its values reflects the differences in user preferences. Therefore the ordinal relations should be reflected in watch time predictions. Second, the conditional dependence between the video-watching behaviors should be captured in the model. For instance, one has to watch half of the video before he/she finishes watching the whole video. Third, modeling watch time with a point estimation ignores the fact that models might give results with high uncertainty and this could cause bad cases in recommender systems. Therefore the framework should be aware of prediction uncertainty. Forth, the real-life recommender systems suffer from severe bias amplifications thus an estimation without bias amplification is expected.

Early action recognition aims at inferring ongoing activities from partial videos as early as possible, whereas conventional action recognition relies on fully observed activities. Observations show that the predictability of different activity subsequences vary wildly, however most existing work failing to fully exploit this phenomenon. We define the predictability of activity subsequences as its capacity to perform recognition early and accurately. A predictability-based early action recognition framework(PEAR) is established to utilize predictability information to achieve early recognition. It consists of a predictability evaluator and a classifier. Due to lacking of fine-grained supervision, we develop a reinforcement-learning-based strategy to optimize the evaluator encouraged by a recognizability reward and an early reward. With the predictability estimated by the evaluator, the classifier learns discriminative representation of subsequences to perform early action recognition without sacrificing much accuracy. Experiments on two benchmark datasets demonstrate the proposed approach outperforms existing methods significantly.