A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases

• URL: http://arxiv.org/abs/2209.11208v1
• Date: Thu, 22 Sep 2022 17:47:21 GMT
• Title: A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
• Authors: James Harrison, Luke Metz, Jascha Sohl-Dickstein
• Abstract summary: Blackbox learneds often struggle with stability and generalization when applied to tasks unlike those in their meta-training set. We investigate the inductive biases and stability properties of optimization algorithms, and apply the resulting insights to designing inductive biases for blackboxs. We learn to a variety of neural network training tasks, where it outperforms the current state of the art learned.
• Score: 44.01339030872185
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge computational expense, blackbox learned optimizers often struggle with stability and generalization when applied to tasks unlike those in their meta-training set. In this paper, we use tools from dynamical systems to investigate the inductive biases and stability properties of optimization algorithms, and apply the resulting insights to designing inductive biases for blackbox optimizers. Our investigation begins with a noisy quadratic model, where we characterize conditions in which optimization is stable, in terms of eigenvalues of the training dynamics. We then introduce simple modifications to a learned optimizer's architecture and meta-training procedure which lead to improved stability, and improve the optimizer's inductive bias. We apply the resulting learned optimizer to a variety of neural network training tasks, where it outperforms the current state of the art learned optimizer -- at matched optimizer computational overhead -- with regard to optimization performance and meta-training speed, and is capable of generalization to tasks far different from those it was meta-trained on.

Related papers

• Narrowing the Focus: Learned Optimizers for Pretrained Models [24.685918556547055]
  We propose a novel technique that learns a layer-specific linear combination of update directions provided by a set of base work tasks. When evaluated on an image, this specialized significantly outperforms both traditional off-the-shelf methods such as Adam, as well existing general learneds.
  arXiv  Detail & Related papers  (2024-08-17T23:55:19Z)
• Investigation into the Training Dynamics of Learned Optimizers [0.0]
  We look at the concept of learneds as a way to accelerate the optimization process by replacing traditional, hand-crafted algorithms with meta-learned functions. Our work examines their optimization from the perspective of network architecture symmetries and update parameters. We identify several key insights that demonstrate how each approach can benefit from the strengths of the other.
  arXiv  Detail & Related papers  (2023-12-12T11:18:43Z)
• HUB: Guiding Learned Optimizers with Continuous Prompt Tuning [45.662334160254176]
  Learneds are a crucial component of meta-learning. Recent advancements in scalable learneds have demonstrated their superior performance over hand-designeds in various tasks. We propose a hybrid-update-based (HUB) optimization strategy to tackle the issue of generalization in scalable learneds.
  arXiv  Detail & Related papers  (2023-05-26T11:08:20Z)
• Learning to Optimize for Reinforcement Learning [58.01132862590378]
  Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learneds do not work well even in simple RL tasks. Agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. We show that, although only trained in toy tasks, our learned can generalize unseen complex tasks in Brax.
  arXiv  Detail & Related papers  (2023-02-03T00:11:02Z)
• VeLO: Training Versatile Learned Optimizers by Scaling Up [67.90237498659397]
  We leverage the same scaling approach behind the success of deep learning to learn versatiles. We train an ingest for deep learning which is itself a small neural network that ingests and outputs parameter updates. We open source our learned, meta-training code, the associated train test data, and an extensive benchmark suite with baselines at velo-code.io.
  arXiv  Detail & Related papers  (2022-11-17T18:39:07Z)
• Training Learned Optimizers with Randomly Initialized Learned Optimizers [49.67678615506608]
  We show that a population of randomly learneds can be used to train themselves from scratch in an online fashion. A form of population based training is used to orchestrate this self-training. We believe feedback loops of this type will be important and powerful in the future of machine learning.
  arXiv  Detail & Related papers  (2021-01-14T19:07:17Z)
• Reverse engineering learned optimizers reveals known and novel mechanisms [50.50540910474342]
  Learneds are algorithms that can themselves be trained to solve optimization problems. Our results help elucidate the previously murky understanding of how learneds work, and establish tools for interpreting future learneds.
  arXiv  Detail & Related papers  (2020-11-04T07:12:43Z)
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves [53.37905268850274]
  We introduce a new, hierarchical, neural network parameterized, hierarchical with access to additional features such as validation loss to enable automatic regularization. Most learneds have been trained on only a single task, or a small number of tasks. We train ours on thousands of tasks, making use of orders of magnitude more compute, resulting in generalizes that perform better to unseen tasks.
  arXiv  Detail & Related papers  (2020-09-23T16:35:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.