`包裹,长文用`
`/`
`划分小节。 3. 列表内容用`
- `,引用用`
`,代码用`
`,重要句子可用``。
4. 保留原文所有信息,不得增删改内容。
5. 不要输出``/``/``等文档级标签。
分析正文内容:
正文是一段关于时间序列预测模型SLiDE的学术新闻/摘要。
"Accurate time series forecasting with exogenous inputs is critical across domains, including energy and retail, yet modern deep learning models often overfit to correlations that do not generalize under shifts in these inputs. We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics. SLiDE approximates nonlinear system evolution using a learned linear operator in a latent space, combining (i) a history encoder that reconstructs the current latent state from past targets and inputs with (ii) a shared linear rollout driven by future exogenous variables. By enforcing a common linear recurrence across encoding and prediction, SLiDE aligns how past information is encoded with how future states evolve, reducing parameterization and preventing reliance on spurious correlations in the input history. Empirically, SLiDE achieves state-of-the-art accuracy on real-world benchmarks, including electricity price forecasting and retail demand, while maintaining a computational footprint comparable to lightweight MLP architectures. SLiDE is especially effective at generalizing to shifted exogenous inputs, reducing MSE by 20% on electricity price samples with out-of-range exogenous values and MAE by 30% in a synthetic transfer setting where the same dynamical system is driven by an unseen exogenous process. Ablations confirm the importance of both the structured history encoder and the linear latent rollout, suggesting that structured latent linear dynamics provide a useful inductive bias for forecasting with exogenous inputs."
这段文本可以划分为几个自然段落或小节,但原文本实际上是一整段。为了符合“长文用/
划分小节”和“每个自然段落用
包裹”,我可以将其合理拆分为几个小节,或者保持为一个长段落但用小标题划分。
考虑到原文是一段连贯的摘要,我可以添加几个小标题来划分,同时保持内容不增删改(标题本身算作排版结构,但为了严格遵守“不得增删改内容”,最好只对原文句子进行包裹,或者把原文拆分为几个`
`,并适当加`
`,代码用``,重要句子可用``。 4. 保留原文所有信息,不得增删改内容。 5. 不要输出``/``/``等文档级标签。 分析正文内容: 正文是一段关于时间序列预测模型SLiDE的学术新闻/摘要。 "Accurate time series forecasting with exogenous inputs is critical across domains, including energy and retail, yet modern deep learning models often overfit to correlations that do not generalize under shifts in these inputs. We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics. SLiDE approximates nonlinear system evolution using a learned linear operator in a latent space, combining (i) a history encoder that reconstructs the current latent state from past targets and inputs with (ii) a shared linear rollout driven by future exogenous variables. By enforcing a common linear recurrence across encoding and prediction, SLiDE aligns how past information is encoded with how future states evolve, reducing parameterization and preventing reliance on spurious correlations in the input history. Empirically, SLiDE achieves state-of-the-art accuracy on real-world benchmarks, including electricity price forecasting and retail demand, while maintaining a computational footprint comparable to lightweight MLP architectures. SLiDE is especially effective at generalizing to shifted exogenous inputs, reducing MSE by 20% on electricity price samples with out-of-range exogenous values and MAE by 30% in a synthetic transfer setting where the same dynamical system is driven by an unseen exogenous process. Ablations confirm the importance of both the structured history encoder and the linear latent rollout, suggesting that structured latent linear dynamics provide a useful inductive bias for forecasting with exogenous inputs." 这段文本可以划分为几个自然段落或小节,但原文本实际上是一整段。为了符合“长文用/
划分小节”和“每个自然段落用
包裹”,我可以将其合理拆分为几个小节,或者保持为一个长段落但用小标题划分。 考虑到原文是一段连贯的摘要,我可以添加几个小标题来划分,同时保持内容不增删改(标题本身算作排版结构,但为了严格遵守“不得增删改内容”,最好只对原文句子进行包裹,或者把原文拆分为几个`
`,并适当加`
`作为小节标题?等等,规则说“不得增删改内容”,如果我加了小标题文字,算不算增加内容? “保留原文所有信息,不得增删改内容”通常指不能改变原文的文字,但可以添加HTML标签。如果添加了`
背景与挑战
`这样的文字,就属于增加了内容。所以,为了安全起见,不添加任何额外的文字标题,只用``包裹段落,或者如果必须用`
/
`,可以用原文中的词作为标题,但原文没有明确的小标题。 或者,我可以把原文按句子或逻辑拆分成几个`
`,不添加小标题,或者将第一句作为小标题?不行,会改变结构。 其实,如果不添加额外的文本,只使用`
`也是符合“每个自然段落用
包裹”的。长文用`
/
`划分小节,如果原文没有明显小节,我可以不使用,或者把原文分成几个自然段,用`
`包裹。 让我们把原文拆分成几个自然段,用`
`包裹,并对重要句子用``。 原文拆分: 段落1:Accurate time series forecasting with exogenous inputs is critical across domains, including energy and retail, yet modern deep learning models often overfit to correlations that do not generalize under shifts in these inputs. We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics. 段落2:SLiDE approximates nonlinear system evolution using a learned linear operator in a latent space, combining (i) a history encoder that reconstructs the current latent state from past targets and inputs with (ii) a shared linear rollout driven by future exogenous variables. By enforcing a common linear recurrence across encoding and prediction, SLiDE aligns how past information is encoded with how future states evolve, reducing parameterization and preventing reliance on spurious correlations in the input history. 段落3:Empirically, SLiDE achieves state-of-the-art accuracy on real-world benchmarks, including electricity price forecasting and retail demand, while maintaining a computational footprint comparable to lightweight MLP architectures. SLiDE is especially effective at generalizing to shifted exogenous inputs, reducing MSE by 20% on electricity price samples with out-of-range exogenous values and MAE by 30% in a synthetic transfer setting where the same dynamical system is driven by an unseen exogenous process. 段落4:Ablations confirm the importance of both the structured history encoder and the linear latent rollout, suggesting that structured latent linear dynamics provide a useful inductive bias for forecasting with exogenous inputs. 重要句子加``: - We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics. - SLiDE achieves state-of-the-art accuracy on real-world benchmarks - Ablations confirm the importance of both the structured history encoder and the linear latent rollout 检查规则: 1. 只输出HTML片段本身,不要Markdown围栏、不要解释。 2. 每个自然段落用`
`包裹,长文用`
`/``划分小节。 (这里没有明显的小节标题,如果不用h2/h3也可以,或者我可以用原文的词组做h3?比如 `
Proposal
` 但这增加了文字。为了严格遵守“不得增删改内容”,不添加任何原文没有的文字。所以只用 `` 和 ``。) 3. 列表用`
- `,引用用`
`,代码用`
`,重要句子可用``。(这里没有列表、引用、代码,所以只用``)。
4. 保留原文所有信息,不得增删改内容。
5. 不要输出``/``/``等文档级标签。
排版后的HTML:
Accurate time series forecasting with exogenous inputs is critical across domains, including energy and retail, yet modern deep learning models often overfit to correlations that do not generalize under shifts in these inputs. We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics.
SLiDE approximates nonlinear system evolution using a learned linear operator in a latent space, combining (i) a history encoder that reconstructs the current latent state from past targets and inputs with (ii) a shared linear rollout driven by future exogenous variables. By enforcing a common linear recurrence across encoding and prediction, SLiDE aligns how past information is encoded with how future states evolve, reducing parameterization and preventing reliance on spurious correlations in the input history.
Empirically, SLiDE achieves state-of-the-art accuracy on real-world benchmarks, including electricity price forecasting and retail demand, while maintaining a computational footprint comparable to lightweight MLP architectures. SLiDE is especially effective at generalizing to shifted exogenous inputs, reducing MSE by 20% on electricity price samples with out-of-range exogenous values and MAE by 30% in a synthetic transfer setting where the same dynamical system is driven by an unseen exogenous process.
Ablations confirm the importance of both the structured history encoder and the linear latent rollout, suggesting that structured latent linear dynamics provide a useful inductive bias for forecasting with exogenous inputs.
检查是否有
`,代码用``,重要句子可用``。(这里没有列表、引用、代码,所以只用``)。 4. 保留原文所有信息,不得增删改内容。 5. 不要输出``/``/``等文档级标签。 排版后的HTML:Accurate time series forecasting with exogenous inputs is critical across domains, including energy and retail, yet modern deep learning models often overfit to correlations that do not generalize under shifts in these inputs. We propose SLiDE, a Koopman-inspired architecture for forecasting with exogenous inputs that imposes structure on latent temporal dynamics.
SLiDE approximates nonlinear system evolution using a learned linear operator in a latent space, combining (i) a history encoder that reconstructs the current latent state from past targets and inputs with (ii) a shared linear rollout driven by future exogenous variables. By enforcing a common linear recurrence across encoding and prediction, SLiDE aligns how past information is encoded with how future states evolve, reducing parameterization and preventing reliance on spurious correlations in the input history.
Empirically, SLiDE achieves state-of-the-art accuracy on real-world benchmarks, including electricity price forecasting and retail demand, while maintaining a computational footprint comparable to lightweight MLP architectures. SLiDE is especially effective at generalizing to shifted exogenous inputs, reducing MSE by 20% on electricity price samples with out-of-range exogenous values and MAE by 30% in a synthetic transfer setting where the same dynamical system is driven by an unseen exogenous process.
Ablations confirm the importance of both the structured history encoder and the linear latent rollout, suggesting that structured latent linear dynamics provide a useful inductive bias for forecasting with exogenous inputs.
检查是否有