AI 与机器学习2016arxiv.org编辑精选
用梯度下降学习如何用梯度下降学习
Learning to learn by gradient descent by gradient descent
进阶 · 约 60 分钟读完前置知识：梯度下降与反向传播、LSTM 基础、优化算法基础（SGD/Adam/RMSprop）
导读
这篇论文提出用梯度下降来训练一个“学习器”（LSTM 网络），让这个学习器学会如何优化另一个网络的目标函数，即“用梯度下降学出梯度下降优化器”。实验表明，学习到的优化器在某些任务上能比手工设计的优化方法（如 SGD、Adam、RMSprop）收敛更快或效果更好。
HN 关注点：“学习如何学习（meta-learning）”这一思路的新颖性，以及它与经典优化方法（牛顿法等）相比的实际效率和实用性。
后来怎么样
这篇论文开创了“学习优化器”（learned optimizers）研究方向，启发了后续一系列元学习优化器的工作，其思想也影响了可学习优化在神经架构搜索等领域的应用。
HN 评论精选
这几条评论里：质疑 1 补充 2 亲历 1
亲历亲历者分享 2001 年用遗传算法做“网络训练网络”的类似尝试，虽未收敛但思路相通
讲个故事：我试过类似的东西，把一个神经网络的输出作为另一个网络的传递权重，用第二个网络的误差来训练第一个网络，但因为不知道如何为反向传播推导传递函数的导数，第一个网络训练不起来。于是我改用随机遗传算法加函数下降来训练第一个网络——事后想想这和生物学的工作方式惊人地接近，但速度极慢。我把训练批次拆开，晚上在大学机房的所有电脑上跑，早上收集各机器上最好的基因，混合后再训练几轮，选出最优个体重新播种到所有机器。折腾了一周，网络始终没能收敛到问题上（任务是用五个间隔 30 度的“距路缘距离”传感器输入开车绕赛道），但这过程真的很有趣！我记得当时是受一家图像识别公司启发，他们用训练网络来训练网络做安防摄像头的运动检测，所以这方法在 2001 年左右也不算全新。总之这让我被一位实验室助教注意到，还拿到了一篇论文……
LoSboccacc查看英文原文
story time: I tried something like this, putting a nnet output as the transfer weight of another neural net and training the first one feeding in the second net input as input and training it on the second net error, but couldn't train the first network because I didn't know how to derive the transfer function for the back propagation algorithm. so I opted for training the first net using a randomized genetic algorithm and function descent on it, which as an afterthought is dangerously close on how biology kind of work, but it was exceptionally slow. so I split up the training batches, went to the uni computer room and left the job running on every computer by night to collect result by morning. in the morning I'd collect the best genes from each machine, mix them all for another few round of training, select the best in the population and reseed them on all the machines by night. after a week of painstakingly organizing, seeding and collecting results, the network never managed to converge around the problem, but boy it was fun trying! The problem was driving a car around a lap of a track using five "distance from kerb" sensor as input angled at 30deg from each other starting from center. I remember I was inspired by an image recognition company, which was using a training network for training network for motion detection over security cameras, so this approach wasn't exactly novelty even back then (2001ish). anyway, this got me noticed by a lab assistant and got a thesis on how to optimize neural network to run in 4.4bit fixed math for use in extra low power devices. that one worked! too bad nothing ever came out of it. edit: some fixin
质疑质疑论文只报迭代次数不报实际耗时，与“牛顿法太慢”的论点自相矛盾
昨天刚（略）读了这篇论文。看起来挺有意思——但论文里没有时间曲线图！一边说“不能用牛顿法因为算 Hessian 太慢”，一边所有性能图都用迭代次数来呈现，这有点稻草人论证的味道。
tansey查看英文原文
Just read (skimmed) this paper yesterday actually. Looks interesting-- but there are no timing graphs! It's kind of a strawman argument to say "We can't use Newton's method because it's too slow to calculate the Hessian," and then go and present all your performance graphs in terms of number of iterations.
补充补充资料：截断牛顿法与论文思路相关且实践中很有效
论文和评论都没提到这个：截断牛顿法（Truncated Newton method）。它用一个只跑几步迭代的内层求解器来近似 Hessian，再用近似 Hessian 近似求解牛顿方程。我实现过，效果非常好，接近解时收敛极快。我提这个是因为它听起来和论文讨论的东西相似，但它的内层求解器用共轭梯度，外层解牛顿方程。
drmeister查看英文原文
Neither the paper nor the comments have mentioned this: https://en.wikipedia.org/wiki/Truncated_Newton_method The Truncated Newton method uses an inner solver that only runs for a few iterations to approximate the Hessian. The approximate Hessian is used to approximately solve Newtons equation. I've implemented it and it works very well. When it gets close to the solution the convergence is very fast. I mention it because it sounds similar to what the paper discusses but you use conjugate gradients in the inner solver and Newton's equation in the outer solver.
补充调侃论文标题的措辞可以更工整
标题本可以选成 "Learn to learn by gradient descent by gradient descent" 或 "Learning learning by gradient descent by gradient descent"。
swehner查看英文原文
The title could have been chosen as "Learn to learn by gradient descent by gradient descent" or "Learning learning by gradient descent by gradient descent"
历次讨论
- 2016Hacker News 讨论帖161 分 · 40 评
同领域还值得读
DeepSeek-R1：通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力，提出 DeepSeek-R1，并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代：面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重，即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2：推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告，延续了 DeepSeek 开源权重模型的路线，目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋（AlphaZero）
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文：用通用强化学习算法（自我博弈 + MCTS + 神经网络），从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor，用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选