Decoupling Gradient-Like Learning Rules from Representations

2018-07-01 · ICML 2018 7 · Philip Thomas, Christoph Dann, Emma Brunskill

In machine learning, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating a machine learning system, we must make two decisions: what representation should be used (i.e., what parameterized function should be used) and what learning rule should be used to search through the resulting set of representable functions. In this paper we focus on gradient-like learning rules, wherein these two decisions are coupled in a subtle (and often unintentional) way. Using most learning rules, these two decisions are coupled in a subtle (and often unintentional) way. That is, using the same learning rule with two different representations that can represent the same sets of functions can result in two different outcomes. After arguing that this coupling is undesirable, particularly when using neural networks, we present a method for partially decoupling these two decisions for a broad class of gradient-like learning rules that span unsupervised learning, reinforcement learning, and supervised learning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning Reinforcement Learning

Decoupling Learning Rules from Representations

2017-06-09 · Philip S. Thomas, Christoph Dann, Emma Brunskill

In the artificial intelligence field, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the paramet…

Reinforcement Learning

Characterizing emergent representations in a space of candidate learning rules for deep networks

2020-12-01 · NeurIPS 2020 12 · Yinan Cao, Christopher Summerfield, Andrew Saxe

How are sensory representations learned via experience? Deep learning offers a theoretical toolkit for studying how neural codes emerge under different learning rules. Studies suggesting that representations in deep netw…

Full-Gradient Successor Feature Representations

2026-04-01 · Ritish Shrirao, Aditya Priyadarshi, Raghuram Bharadwaj Diddigi arxiv

Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL) by decoupling environment dynamics from reward functions. However…

Reinforcement Learning Transfer Learning

Decoupling Search and Learning in Neural Net Training

2025-09-13 · Akshay Vegesna, Samip Dahal arxiv

Gradient descent typically converges to a single minimum of the training loss without mechanisms to explore alternative minima that may generalize better. Searching for diverse minima directly in high-dimensional paramet…

Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules

2025-10-30 · John J. Vastola, Samuel J. Gershman, Kanaka Rajan arxiv

Learning rules -- prescriptions for updating model parameters to improve performance -- are typically assumed rather than derived. Why do some learning rules work better than others, and under what assumptions can a give…

Continual Learning Bayesian Inference