按年被提到
20212023 · 2 次2026
机器学习与深度学习›优化与可微编程·arXiv:2111.05803 · cs.LG

Gradients are Not All You Need

Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz, Tal Kachman · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2021-11-11 · 最近 2023-04-23
3不同的人
2活跃月份
2讨论串
46被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Differentiable programming techniques are widely used in the community and are responsible for the machine learning renaissance of the past several decades. While these methods are powerful, they have limits. In this short report, we discuss a common chaos based failure mode which appears in a variety of differentiable circumstances, ranging from recurrent neural networks and numerical physics simulation to training learned optimizers. We trace this failure to the spectrum of the Jacobian of the system under study, and provide criteria for when a practitioner might expect this failure to spoil their differentiation based optimization algorithms.

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tough · 2023-04

“I asked GPT > https://arxiv.org/abs/2111.05803 make a good useful title that's not silly for this paper and wht's about I dunno if it even read the article lols ==== Title: “Deep Reinforcement Learning for Multi-Agent Navigation in Complex Environments” This paper proposes a deep reinforcement learning approach for multi-agent navigation in complex env…”

Gradients Are Not All You Need原评论 ↗
被提交为 story · 2 次