arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09201cs.LGstat.ML
收藏

优于KL的PAC-Bayes界

Better-than-KL PAC-Bayes Bounds

Google DeepMind(谷歌DeepMind);University of Arizona(亚利桑那大学);KAUST(阿卜杜拉国王科技大学);New York University(纽约大学)

Ilja Kuzborskij, Kwang-Sung Jun, Yulian Wu, Kyoungseok Jang, Francesco Orabona

AI总结:

本文提出一种新颖的优于KL散度的PAC-Bayes界,受赌博算法遗憾分析启发,首次证明非KL散度界可严格优于KL,为确定PAC-Bayes界最优速率迈出第一步。

摘要:

设 $f(θ, X_1),$ $ \dots,$ $ f(θ, X_n)$ 为一列随机元素,其中 $f$ 是一个固定的标量函数,$X_1, \dots, X_n$ 是独立随机变量(数据),$θ$ 是根据某个依赖于数据的后验分布 $P_n$ 分布的随机参数。本文考虑证明集中不等式以估计该序列均值的问题。这类问题的一个例子是估计由随机算法训练的某个预测器的泛化误差,例如神经网络,其中 $f$ 是损失函数。经典上,该问题通过PAC-Bayes分析来处理,其中除了后验分布之外,我们选择一个先验分布来刻画我们对学习问题归纳偏置的信念。然后,PAC-Bayes集中界中的关键量是一个刻画学习问题复杂度的散度,其中事实上的标准选择是KL散度。然而,这一选择的紧致性很少受到质疑。本文通过证明有可能实现严格更紧的界,对基于KL散度的界的紧致性提出挑战。特别地,我们展示了新的高概率PAC-Bayes界,采用一种受Zhang等人(2022)启发的新颖且优于KL的散度。我们的证明受到赌博算法遗憾分析的最新进展及其用于推导集中不等式的启发。我们的结果是首创性的,因为现有的使用非KL散度的PAC-Bayes界尚不知道是否严格优于KL。因此,我们相信我们的工作标志着迈向确定PAC-Bayes界最优速率的第一步。

英文摘要:

Let $f(θ, X_1),$ $ \dots,$ $ f(θ, X_n)$ be a sequence of random elements, where $f$ is a fixed scalar function, $X_1, \dots, X_n$ are independent random variables (data), and $θ$ is a random parameter distributed according to some data-dependent posterior distribution $P_n$. In this paper, we consider the problem of proving concentration inequalities to estimate the mean of the sequence. An example of such a problem is the estimation of the generalization error of some predictor trained by a stochastic algorithm, such as a neural network where $f$ is a loss function. Classically, this problem is approached through a PAC-Bayes analysis where, in addition to the posterior, we choose a prior distribution which captures our belief about the inductive bias of the learning problem. Then, the key quantity in PAC-Bayes concentration bounds is a divergence that captures the complexity of the learning problem where the de facto standard choice is the KL divergence. However, the tightness of this choice has rarely been questioned. In this paper, we challenge the tightness of the KL-divergence-based bounds by showing that it is possible to achieve a strictly tighter bound. In particular, we demonstrate new high-probability PAC-Bayes bounds with a novel and better-than-KL divergence that is inspired by Zhang et al. (2022). Our proof is inspired by recent advances in regret analysis of gambling algorithms, and its use to derive concentration inequalities. Our result is first-of-its-kind in that existing PAC-Bayes bounds with non-KL divergences are not known to be strictly better than KL. Thus, we believe our work marks the first step towards identifying optimal rates of PAC-Bayes bounds.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑