Long-term time series forecasting (LTSF) is important for various domains but is confronted by challenges in handling the complex temporal-contextual relationships. As multivariate input models underperforming some recent univariate counterparts, we posit that the issue lies in the inefficiency of existing multivariate LTSF Transformers to model series-wise relationships: the characteristic differences between series are often captured incorrectly. To address this, we introduce ARM: a multivariate temporal-contextual adaptive learning method, which is an enhanced architecture specifically designed for multivariate LTSF modelling. ARM employs Adaptive Univariate Effect Learning (AUEL), Random Dropping (RD) training strategy, and Multi-kernel Local Smoothing (MKLS), to better handle individual series temporal patterns and correctly learn inter-series dependencies. ARM demonstrates superior performance on multiple benchmarks without significantly increasing computational costs compared to vanilla Transformer, thereby advancing the state-of-the-art in LTSF. ARM is also generally applicable to other LTSF architecture beyond vanilla Transformer.
ARMA Block: A CNN-Based Autoregressive and Moving Average Module for Long-Term Time Series Forecasting
AI Lab, Grepp（Grepp人工智能实验室）；Department of Computer Science and Engineering, Hankuk University of Foreign Studies（韩国外国语大学计算机科学与工程系）；Department of Radiation Physics, The University of Texas MD Anderson Cancer Center（德克萨斯MD安德森癌症中心辐射物理系）
Multi-objective Contextual Bandit Problem with Similarity Information
Bilkent University（比尔肯特大学）
在本文中，我们提出了多目标上下文强盗问题的相似信息。这个问题扩展了经典的上下文强盗问题的相似性信息，通过引入多个和可能冲突的目标。由于每个目标中的最佳手臂在给定的背景下可能是不同的，因此基于单个目标学习最佳手臂可能会危及从其他目标获得的奖励。为了评估学习者在这种设置中的表现，我们使用了一个性能指标，称为上下文帕累托后悔。从本质上讲，语境帕累托后悔是学习者选择的手臂到语境相关帕累托前沿的距离之和。对于这个问题，我们开发了一种新的在线学习算法，称为帕累托上下文缩放（PCZ），它利用上下文缩放的思想来学习的手臂接近帕累托前面的每个观察到的上下文，通过自适应分区的联合上下文手臂集根据观察到的奖励和位置的上下文手臂对在过去选择。然后，我们证明了PCZ实现了$\tilde O (T^{(1+d_p)/(2+d_p)})$帕累托后悔，其中$d_p$是帕累托缩放维度，取决于一组接近最优的上下文臂对的大小。此外，我们通过提供几乎匹配的$Ω(T^{(1+d_p)/(2+d_p)})$下界来证明该遗憾界几乎是最优的。
Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs
Georgia Institute of Technology（佐治亚理工学院）
本文考虑了风险厌恶准则下线性支付的上下文多臂强盗问题。在每一轮中，每只手臂的上下文都被揭示出来，决策者选择一只手臂来拉动，并获得相应的奖励。特别地，我们考虑均值-方差作为风险标准，最佳臂是具有最大均值-方差回报的臂。我们应用汤普森采样算法的不相交模型，并提供了一个全面的遗憾分析所提出的算法的一个变体。对于$T$轮，$K$行动，和$d$维特征向量，我们证明了遗憾界的$O((1+ρ+\frac{1}ρ) d\ln T \ln \frac{K}δ\sqrt{d K T^{1+2ε} \ln \frac{K}δ \frac{1}ε})$，持有概率$1-δ$下的均值方差准则与风险容忍度$ρ$，任何$0<ε<\frac{1}{2}$，$0<δ<1$。我们所提出的算法的实证表现证明通过一个投资组合选择问题。
Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Department of Computer and Communication Sciences（计算机与通信科学系）；Department of Electrical and Electronics Engineering（电气与电子工程系）
Adaptive Bandit Algorithms for Contextual Matching Markets
Center for Statistical Science, School of Mathematical Sciences, Peking University（北京大学数学科学学院统计科学中心）；INRIA, FairPlay Joint Team（INRIA公平玩联合团队）；Criteo AI lab, FairPlay Joint Team（Criteo AI实验室，公平玩联合团队）；Technion - Israel Institute of Technology（技术学院-以色列理工学院）
Data Analytics Team, Mizuho–DL Financial Technology, Co., Ltd.（摩根大通数字金融技术公司数据分析团队）；Department of Economics, Northwestern University（西北大学经济学系）；Graduate School of Economics and Management, Tohoku University（东北大学经济学与管理学院）；Department of Economics, Brown University（布朗大学经济学系）
