Continual learning with the neural tangent ensemble

• URL: http://arxiv.org/abs/2408.17394v1
• Date: Fri, 30 Aug 2024 16:29:09 GMT
• Title: Continual learning with the neural tangent ensemble
• Authors: Ari S. Benjamin, Christian Pehle, Kyle Daruwalla,
• Abstract summary: We show that a neural network with N parameters can be interpreted as a weighted ensemble of N classifiers. We derive the likelihood and posterior probability of each expert given past data. Surprisingly, we learn that the posterior updates for these experts are equivalent to a scaled and projected form of gradient descent.
• Score: 0.6137178191238463
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A natural strategy for continual learning is to weigh a Bayesian ensemble of fixed functions. This suggests that if a (single) neural network could be interpreted as an ensemble, one could design effective algorithms that learn without forgetting. To realize this possibility, we observe that a neural network classifier with N parameters can be interpreted as a weighted ensemble of N classifiers, and that in the lazy regime limit these classifiers are fixed throughout learning. We term these classifiers the neural tangent experts and show they output valid probability distributions over the labels. We then derive the likelihood and posterior probability of each expert given past data. Surprisingly, we learn that the posterior updates for these experts are equivalent to a scaled and projected form of stochastic gradient descent (SGD) over the network weights. Away from the lazy regime, networks can be seen as ensembles of adaptive experts which improve over time. These results offer a new interpretation of neural networks as Bayesian ensembles of experts, providing a principled framework for understanding and mitigating catastrophic forgetting in continual learning settings.

Related papers

• Taming Binarized Neural Networks and Mixed-Integer Programs [2.7624021966289596]
  We show that binarized neural networks admit a tame representation. This makes it possible to use the framework of Bolte et al. for implicit differentiation. This approach could also be used for a broader class of mixed-integer programs.
  arXiv  Detail & Related papers  (2023-10-05T21:04:16Z)
• Utility-Probability Duality of Neural Networks [4.871730595406078]
  We propose an alternative utility-based explanation to the standard supervised learning procedure in deep learning. The basic idea is to interpret the learned neural network not as a probability model but as an ordinal utility function. We show that for all neural networks with softmax outputs, the SGD learning dynamic of maximum likelihood estimation can be seen as an iteration process.
  arXiv  Detail & Related papers  (2023-05-24T08:09:07Z)
• Benign Overfitting for Two-layer ReLU Convolutional Neural Networks [60.19739010031304]
  We establish algorithm-dependent risk bounds for learning two-layer ReLU convolutional neural networks with label-flipping noise. We show that, under mild conditions, the neural network trained by gradient descent can achieve near-zero training loss and Bayes optimal test risk.
  arXiv  Detail & Related papers  (2023-03-07T18:59:38Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations [2.047424180164312]
  We study the expectation of a probabilistic neural network as a predictor by itself, focusing on the aggregation of binary activated neural networks with normal distributions over real-valued weights. We show that the exact computation remains tractable for deep but narrow neural networks, thanks to a dynamic programming approach.
  arXiv  Detail & Related papers  (2021-10-28T14:11:07Z)
• Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks [79.74580058178594]
  We analyze the performance of training a pruned neural network by analyzing the geometric structure of the objective function. We show that the convex region near a desirable model with guaranteed generalization enlarges as the neural network model is pruned.
  arXiv  Detail & Related papers  (2021-10-12T01:11:07Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• FF-NSL: Feed-Forward Neural-Symbolic Learner [70.978007919101]
  This paper introduces a neural-symbolic learning framework, called Feed-Forward Neural-Symbolic Learner (FF-NSL) FF-NSL integrates state-of-the-art ILP systems based on the Answer Set semantics, with neural networks, in order to learn interpretable hypotheses from labelled unstructured data.
  arXiv  Detail & Related papers  (2021-06-24T15:38:34Z)
• Fast Adaptation with Linearized Neural Networks [35.43406281230279]
  We study the inductive biases of linearizations of neural networks, which we show to be surprisingly good summaries of the full network functions. Inspired by this finding, we propose a technique for embedding these inductive biases into Gaussian processes through a kernel designed from the Jacobian of the network. In this setting, domain adaptation takes the form of interpretable posterior inference, with accompanying uncertainty estimation.
  arXiv  Detail & Related papers  (2021-03-02T03:23:03Z)
• Compressive Sensing and Neural Networks from a Statistical Learning Perspective [4.561032960211816]
  We present a generalization error analysis for a class of neural networks suitable for sparse reconstruction from few linear measurements. Under realistic conditions, the generalization error scales only logarithmically in the number of layers, and at most linear in number of measurements.
  arXiv  Detail & Related papers  (2020-10-29T15:05:43Z)

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.