PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding

• URL: http://arxiv.org/abs/2111.08792v2
• Date: Fri, 5 May 2023 15:05:24 GMT
• Title: PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding
• Abstract summary: We present PredProp, a method for optimization of weights and states in predictive coding networks (PCNs) PredProp addresses inference and learning via gradient descent and adaptively updates parameter by approximate curvature. We demonstrate PredProp's effectiveness in the context of dense decoder networks and simple image benchmark datasets.
• Score: 1.5229257192293197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present PredProp, a method for optimization of weights and states in predictive coding networks (PCNs) based on the precision of propagated errors and neural activity. PredProp jointly addresses inference and learning via stochastic gradient descent and adaptively weights parameter updates by approximate curvature. Due to the relation between propagated error covariance and the Fisher information matrix, PredProp implements approximate Natural Gradient Descent. We demonstrate PredProp's effectiveness in the context of dense decoder networks and simple image benchmark datasets. We found that PredProp performs favorably over Adam, a widely used adaptive learning rate optimizer in the tested configurations. Furthermore, available optimization methods for weight parameters benefit from using PredProp's error precision during inference. Since hierarchical predictive coding layers are optimised individually using local errors, the required precisions factorize over hierarchical layers. Extending beyond classical PCNs with a single set of decoder layers per hierarchical layer, we also generalize PredProp to deep neural networks in each PCN layer by additionally factorizing over the weights in each PCN layer.

Related papers

• Curvature-Guided LoRA: Steering in the pretrained NTK subspace [60.35296431630704]
  We introduce the prediction alignment problem, aiming to match the predictor obtained via PEFT to that of full fine-tuning at the level of outputs.<n>We show that this objective naturally leads to a curvature-aware, second-order formulation, where optimal low-rank updates correspond to a Newton-like, curvature-whitened gradient.<n>Based on this insight, we propose Curvature-Guided LoRA (CG-LoRA), which selects and scales adaptation directions using local curvature information.
  arXiv  Detail & Related papers  (2026-03-31T14:46:39Z)
• Soft regression trees: a model variant and a decomposition training algorithm [0.24578723416255752]
  We propose a new variant of soft multivariate regression trees (SRTs) where, for every input vector, the prediction is defined as a linear regression associated to a single leaf node. SRTs exhibit the conditional computational property, i.e., each prediction depends on a small number of nodes. Experiments on 15 wellknown datasets indicate that our SRTs and decomposition algorithm yield higher accuracy and robustness compared with traditional soft regression trees.
  arXiv  Detail & Related papers  (2025-01-10T13:06:36Z)
• PropNEAT -- Efficient GPU-Compatible Backpropagation over NeuroEvolutionary Augmenting Topology Networks [1.9424018922013226]
  PropNEAT is a fast backpropagation implementation of NEAT that uses a bidirectional mapping of the genome graph to a layer-based architecture. We test PropNEAT on 58 binary classification datasets from the Penn Machine Learning Benchmarks database.
  arXiv  Detail & Related papers  (2024-11-06T07:44:14Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• PPI++: Efficient Prediction-Powered Inference [31.403415618169433]
  We present PPI++: a methodology for estimation and inference based on a small labeled dataset and a typically much larger dataset of machine-learning predictions. The methods automatically adapt to the quality of available predictions, yielding easy-to-compute confidence sets. PPI++ builds on prediction-powered inference (PPI), which targets the same problem setting, improving its computational and statistical efficiency.
  arXiv  Detail & Related papers  (2023-11-02T17:59:04Z)
• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• Set-based Neural Network Encoding Without Weight Tying [91.37161634310819]
  We propose a neural network weight encoding method for network property prediction.<n>Our approach is capable of encoding neural networks in a model zoo of mixed architecture.<n>We introduce two new tasks for neural network property prediction: cross-dataset and cross-architecture.
  arXiv  Detail & Related papers  (2023-05-26T04:34:28Z)
• Efficient and Differentiable Conformal Prediction with General Function Classes [96.74055810115456]
  We propose a generalization of conformal prediction to multiple learnable parameters. We show that it achieves approximate valid population coverage and near-optimal efficiency within class. Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly.
  arXiv  Detail & Related papers  (2022-02-22T18:37:23Z)
• Curvature Injected Adaptive Momentum Optimizer for Convolutional Neural Networks [21.205976369691765]
  We propose a new approach, hereafter referred as AdaInject, for the descent gradients. The curvature information is used as a weight to inject the second order moment in the update rule. The AdaInject approach boosts the parameter update by exploiting the curvature information.
  arXiv  Detail & Related papers  (2021-09-26T06:24:14Z)
• Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? [59.820507600960745]
  We propose a new GCP meta-layer that uses SVD in the forward pass, and Pad'e Approximants in the backward propagation to compute the gradients. The proposed meta-layer has been integrated into different CNN models and achieves state-of-the-art performances on both large-scale and fine-grained datasets.
  arXiv  Detail & Related papers  (2021-05-06T08:03:45Z)
• A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks [0.0]
  optimization of Binary Neural Networks (BNNs) relies on approximating the real-valued weights with their binarized representations. In this paper, we take an approach parallel to Adam which also uses the second raw moment estimate to normalize the first raw moment before doing the comparison with the threshold. We present two versions of the proposed: a biased one and a bias-corrected one, each with its own applications.
  arXiv  Detail & Related papers  (2021-04-11T22:20:09Z)
• Exploiting Adam-like Optimization Algorithms to Improve the Performance of Convolutional Neural Networks [82.61182037130405]
  gradient descent (SGD) is the main approach for training deep networks. In this work, we compare Adam based variants based on the difference between the present and the past gradients. We have tested ensemble of networks and the fusion with ResNet50 trained with gradient descent.
  arXiv  Detail & Related papers  (2021-03-26T18:55:08Z)
• PEP: Parameter Ensembling by Perturbation [13.221295194854642]
  Ensembling by Perturbation (PEP) constructs an ensemble of parameter values as random perturbations of the optimal parameter set from training. PEP provides a small improvement in performance, and, in some cases, a substantial improvement in empirical calibration. PEP can be used to probe the level of overfitting that occurred during training.
  arXiv  Detail & Related papers  (2020-10-24T00:16:03Z)
• Predictive Coding Approximates Backprop along Arbitrary Computation Graphs [68.8204255655161]
  We develop a strategy to translate core machine learning architectures into their predictive coding equivalents. Our models perform equivalently to backprop on challenging machine learning benchmarks. Our method raises the potential that standard machine learning algorithms could in principle be directly implemented in neural circuitry.
  arXiv  Detail & Related papers  (2020-06-07T15:35:47Z)

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.