Neural Scaling Laws From Large-N Field Theory: Solvable Model Beyond the Ridgeless Limit
- URL: http://arxiv.org/abs/2405.19398v1
- Date: Wed, 29 May 2024 18:00:01 GMT
- Title: Neural Scaling Laws From Large-N Field Theory: Solvable Model Beyond the Ridgeless Limit
- Authors: Zhengkang Zhang,
- Abstract summary: We use large-N field theory methods to solve a model proposed by Maloney, Roberts and Sully.
We uncover a duality transformation at the diagrams level which explains the symmetry between model and training data set sizes.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many machine learning models based on neural networks exhibit scaling laws: their performance scales as power laws with respect to the sizes of the model and training data set. We use large-N field theory methods to solve a model recently proposed by Maloney, Roberts and Sully which provides a simplified setting to study neural scaling laws. Our solution extends the result in this latter paper to general nonzero values of the ridge parameter, which are essential to regularize the behavior of the model. In addition to obtaining new and more precise scaling laws, we also uncover a duality transformation at the diagrams level which explains the symmetry between model and training data set sizes. The same duality underlies recent efforts to design neural networks to simulate quantum field theories.
Related papers
- Information-Theoretic Foundations for Neural Scaling Laws [20.617552198581024]
We develop information-theoretic foundations for neural scaling laws.
We observe that the optimal relation between data and model size is linear, up to logarithmic factors.
arXiv Detail & Related papers (2024-06-28T02:20:54Z) - Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
This paper introduces the SANE approach to weight-space learning.
Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
arXiv Detail & Related papers (2024-06-14T13:12:07Z) - Mixtures of Experts Unlock Parameter Scaling for Deep RL [54.26191237981469]
In this paper, we demonstrate that incorporating Mixture-of-Expert (MoE) modules into value-based networks results in more parameter-scalable models.
This work thus provides strong empirical evidence towards developing scaling laws for reinforcement learning.
arXiv Detail & Related papers (2024-02-13T17:18:56Z) - A Dynamical Model of Neural Scaling Laws [79.59705237659547]
We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization.
Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
arXiv Detail & Related papers (2024-02-02T01:41:38Z) - Learning Neural Constitutive Laws From Motion Observations for
Generalizable PDE Dynamics [97.38308257547186]
Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models.
We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned.
We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
arXiv Detail & Related papers (2023-04-27T17:42:24Z) - The Quantization Model of Neural Scaling [19.057931064238584]
We propose the Quantization Model of neural scaling laws, explaining both the observed power law dropoff of loss with model and data size, and the sudden emergence of new capabilities with scale.
We show that when quanta are learned in order of decreasing use frequency, then a power law in use explains observed power law scaling of loss.
arXiv Detail & Related papers (2023-03-23T17:58:43Z) - A Solvable Model of Neural Scaling Laws [72.8349503901712]
Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws.
We propose a statistical model -- a joint generative data model and random feature model -- that captures this neural scaling phenomenology.
Key findings are the manner in which the power laws that occur in the statistics of natural datasets are extended by nonlinear random feature maps.
arXiv Detail & Related papers (2022-10-30T15:13:18Z) - Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics.
Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization.
Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
arXiv Detail & Related papers (2022-10-13T10:00:30Z) - Scaling Laws for Acoustic Models [7.906034575114518]
Recent work has shown that autoregressive generative models with cross-entropy objective functions exhibit smooth power-law relationships.
We show that acoustic models trained with an auto-predictive coding loss behave as if they are subject to similar scaling laws.
arXiv Detail & Related papers (2021-06-11T18:59:24Z)
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.