Gradient Surgery for Multi-Task Learning

Web Reference: 我会使用尽量少的数学符号描述 梯度， 着重于意义而非计算。一个直观的例子，在机器学习领域有个术语叫「梯度下降」，你可以想象在群山之中，某个山的半山腰有只小兔子打算使用梯度下降的思路去往这片群山最深的山谷里找水喝。 我们用 变化率 来描述下山时各个方向的山路有多陡峭，往下 ... 为了降低随机梯度的方差，从而使得迭代算法更加稳定，也为了充分利用高度优化的矩阵运算操作，在实际应用中我们会同时处理若干训练数据，该方法被称为小批量梯度下降法 (Mini- Batch Gradient Descent)。 假设需要同时处理m个训练数据 则目标函数及其梯度为 这篇回答节选自我的专栏 《机器学习中的数学：微积分与最优化》，和大家一起谈谈方向导数和梯度。 欢迎关注我的知乎账号 @石溪 ，将持续发布机器学习数学基础及算法应用等方面的精彩内容。 1.多元函数偏导数的数值解 在程序当中，利用数值方法求出各个自变量偏导数的近似解，其方法和步骤 ...

YouTube Excerpt: Multi-Task Learning can be very challenging when gradients of different tasks are of severely different magnitudes or point into conflicting directions. PCGrad eliminates this problem by projecting conflicting gradients while still retaining optimality guarantees. https://arxiv.org/abs/2001.06782 Abstract: While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks to enable more efficient learning. However, the multi-task setting presents a number of optimization challenges, making it difficult to realize large efficiency gains compared to learning tasks independently. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a conflicting gradient. On a series of challenging multi-task supervised and multi-task RL problems, this approach leads to substantial gains in efficiency and performance. Further, it is model-agnostic and can be combined with previously-proposed multi-task architectures for enhanced performance. Authors: Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://www.bitchute.com/channel/yannic-kilcher Minds: https://www.minds.com/ykilcher

Multi-Task Learning can be very challenging when gradients of different tasks are of severely different magnitudes or point into conflicting...

Read Full Article 🔍

Curious about Gradient Surgery For Multi-Task Learning's Color? Explore detailed estimates, salary breakdowns, and financial insights that reveal the true scope of their profile.

Source ID: PZypP7PiKi0

Category: color style guide