`包裹,长文用`
`/`
`划分小节(这里文本不长,可以直接用`
`,或者适当加个标题,但原文没有标题,所以不用强加,或者把第一句作为小标题?规则说“长文用
/
划分小节”,这里只有一段长文本,可以直接用`
`包裹,或者拆分成几个`
`。原文是一整段,为了排版好看,可以保持一个`
`,或者按句子拆分成多个`
`。最好是把原文的几个长句分别用`
`包裹,或者整个作为一段。根据“每个自然段落用
包裹”,原文是一个自然段,所以用一个`
`包裹即可。不过为了体现“排版工程师”的专业感,可以把一些重要的句子用``,或者把核心结论用`
`?规则说“重要句子可用”,但“不得增删改内容”。我可以把整段放在一个``里,部分重要句子加``。 3. 列表用`
- `,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。 分析原文: "We study statistical inference for online sketched Newton methods, in which each Newton system is approximately solved by an inner randomized sketching solver. Existing work reveals a computational--statistical trade-off: the sketching solver (and its accelerated variants) reduces the per-step cost of Newton methods from $O(d^3)$ to $O(d^2)$, but the randomness introduced by sketching also inflates the limiting covariance of both the last and the averaged Newton iterates. In this work, we address this trade-off via gradient averaging. We show that simply replacing the stochastic gradient with a moving average at each step can mitigate, and in some cases eliminate, the trade-off in Newton sketch. Importantly, gradient averaging requires no additional oracle evaluations and leaves the contraction bound of the inner sketching solver unchanged. In particular, we prove that the last sketched Newton iterate with gradient averaging attains a limiting covariance no larger than that without gradient averaging, while the averaged iterate even attains the minimax optimal limiting covariance, matching that of the exact Newton method. To our knowledge, this is the first analysis showing that randomness introduced to improve computational efficiency need not compromise statistical efficiency as long as proper gradient estimates are used. The key analytical challenge is that gradient averaging destroys the crucial martingale difference structure underlying central limit theorem arguments. We overcome this challenge by analyzing the coupled two-timescale recursions governing the iterate and the gradient estimator. Numerical experiments on linear and logistic regression support our theoretical covariance comparisons." 可以将其拆分为几个自然段落(虽然原文是一整段,但在HTML排版中,为了阅读体验,可以将逻辑上的部分拆分,但规则说“每个自然段落用包裹”,如果原文只有一个自然段,那就只用一个`
`。为了安全,不改变原文的段落结构,原文就是一段,所以用一个`
`。 或者,把原文分成几个`
`,按句号拆分,但这改变了“自然段落”的定义。最好保持原文的段落结构。原文是一整段。 重要句子加``: - "We study statistical inference for online sketched Newton methods..." - "Existing work reveals a computational--statistical trade-off..." - "In this work, we address this trade-off via gradient averaging." - "We show that simply replacing the stochastic gradient with a moving average at each step can mitigate, and in some cases eliminate, the trade-off in Newton sketch." - "Importantly, gradient averaging requires no additional oracle evaluations and leaves the contraction bound of the inner sketching solver unchanged." - "In particular, we prove that the last sketched Newton iterate with gradient averaging attains a limiting covariance no larger than that without gradient averaging, while the averaged iterate even attains the minimax optimal limiting covariance, matching that of the exact Newton method." - "To our knowledge, this is the first analysis showing that randomness introduced to improve computational efficiency need not compromise statistical efficiency as long as proper gradient estimates are used." - "The key analytical challenge is that gradient averaging destroys the crucial martingale difference structure underlying central limit theorem arguments." - "We overcome this challenge by analyzing the coupled two-timescale recursions governing the iterate and the gradient estimator." - "Numerical experiments on linear and logistic regression support our theoretical covariance comparisons." 不需要强行加`
`或`
`,因为原文没有小节标题,强行加会违反“不得增删改内容”。 不需要`
`,没有列表。 不需要`
`,没有引用。 不需要``,没有代码。 可以将核心结论用``标出,比如: `We study statistical inference for online sketched Newton methods, in which each Newton system is approximately solved by an inner randomized sketching solver. Existing work reveals a computational--statistical trade-off: the sketching solver (and its accelerated variants) reduces the per-step cost of Newton methods from $O(d^3)$ to $O(d^2)$, but the randomness introduced by sketching also inflates the limiting covariance of both the last and the averaged Newton iterates. In this work, we address this trade-off via gradient averaging. We show that simply replacing the stochastic gradient with a moving average at each step can mitigate, and in some cases eliminate, the trade-off in Newton sketch. Importantly, gradient averaging requires no additional oracle evaluations and leaves the contraction bound of the inner sketching solver unchanged. In particular, we prove that the last sketched Newton iterate with gradient averaging attains a limiting covariance no larger than that without gradient averaging, while the averaged iterate even attains the minimax optimal limiting covariance, matching that of the exact Newton method. To our knowledge, this is the first analysis showing that randomness introduced to improve computational efficiency need not compromise statistical efficiency as long as proper gradient estimates are used. The key analytical challenge is that gradient averaging destroys the crucial martingale difference structure underlying central limit theorem arguments. We overcome this challenge by analyzing the coupled two-timescale recursions governing the iterate and the gradient estimator. Numerical experiments on linear and logistic regression support our theoretical covariance comparisons.
` 检查规则: 1. 只输出HTML片段本身,不要Markdown围栏、不要解释。 -> 满足。 2. 每个自然段落用包裹,长文用
/
划分小节。 -> 原文只有一段,用
包裹。没有长文需要划分小节。 3. 列表内容用
- ,引用用
,代码用,重要句子可用。 -> 使用了。 4. 保留原文所有信息,不得增删改内容。 -> 满足,仅添加了HTML标签。 5. 不要输出//等文档级标签。 -> 满足。 再审视一下,是否有遗漏的格式要求? "长文用/
划分小节" - 如果原文没有小节,就不需要硬加,否则就属于“增改内容”。所以只用`
`和``是合理的。 确认HTML标签拼写正确,没有多余空格。 `
We study statistical inference for online sketched Newton methods, in which each Newton system is approximately solved by an inner randomized sketching solver. Existing work reveals a computational--statistical trade-off: the sketching solver (and its accelerated variants) reduces the per-step cost of Newton methods from $O(d^3)$ to $O(d^2)$, but the randomness introduced by sketching also inflates the limiting covariance of both the last and the averaged Newton iterates. In this work, we address this trade-off via gradient averaging. We show that simply replacing the stochastic gradient with a moving average at each step can mitigate, and in