按年被提到
20232023 · 1 次2026
机器学习与深度学习›贝叶斯方法与 AutoML·arXiv:2305.03515 · cs.LG

GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent

Sascha Marton, Stefan Lüdtke, Christian Bartelt, Heiner Stuckenschmidt · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-11-05 · 最近 2024-06-22
2不同的人
2活跃月份
2讨论串
7被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The method is available under: https://github.com/s-marton/GradTree

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论cgreerrun · 2023-11

“You can use the straight through operator! During the forward pass you sample a discrete outcome given your NN weights to get an error for backprop. During the backward pass you directly propogate through the weights. This GradTree paper[1] does a good job covering how to do discrete gradient-based optimization (i.e. NNs w/ discrete representations). A…”

Kolmogorov Neural Networks can represent discontinuous functions原评论 ↗
评论sitkack · 2024-06

“There is some work to convert NNs to decision trees. https://towardsdatascience.com/neural-networks-as-decision-trees-89cd9fdcdf6a https://arxiv.org/abs/2210.05189 I haven't reviewed any of it, I only know of it tangentially. https://www.semanticscholar.org/paper/Converting-A-Trained-Neural-Network-To-a-Decision-Boz/fb6172737873a69bd8d0117c88301121b5c…”

20x Faster Background Removal in the Browser Using ONNX Runtime with WebGPU原评论 ↗