Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units

• URL: http://arxiv.org/abs/2110.07700v1
• Date: Thu, 14 Oct 2021 20:18:38 GMT
• Title: Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units
• Authors: Kenny Young
• Abstract summary: We present Hindsight Network Credit Assignment (HNCA), a novel learning algorithm for networks of discrete units. HNCA works by assigning credit to each unit based on the degree to which its output influences its immediate children in the network. We show how HNCA can be extended to optimize a more general function of the outputs of a network of units, where the function is known to the agent.
• Score: 2.28438857884398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training neural networks with discrete stochastic variables presents a unique challenge. Backpropagation is not directly applicable, nor are the reparameterization tricks used in networks with continuous stochastic variables. To address this challenge, we present Hindsight Network Credit Assignment (HNCA), a novel learning algorithm for networks of discrete stochastic units. HNCA works by assigning credit to each unit based on the degree to which its output influences its immediate children in the network. We prove that HNCA produces unbiased gradient estimates with reduced variance compared to the REINFORCE estimator, while the computational cost is similar to that of backpropagation. We first apply HNCA in a contextual bandit setting to optimize a reward function that is unknown to the agent. In this setting, we empirically demonstrate that HNCA significantly outperforms REINFORCE, indicating that the variance reduction implied by our theoretical analysis is significant and impactful. We then show how HNCA can be extended to optimize a more general function of the outputs of a network of stochastic units, where the function is known to the agent. We apply this extended version of HNCA to train a discrete variational auto-encoder and empirically show it compares favourably to other strong methods. We believe that the ideas underlying HNCA can help stimulate new ways of thinking about efficient credit assignment in stochastic compute graphs.

Related papers

• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE is a self-supervised learning framework that enhances global feature representation of point cloud mask autoencoders. We show that PseudoNeg-MAE achieves state-of-the-art performance on the ModelNet40 and ScanObjectNN datasets.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Theoretical Characterization of How Neural Network Pruning Affects its Generalization [131.1347309639727]
  This work makes the first attempt to study how different pruning fractions affect the model's gradient descent dynamics and generalization. It is shown that as long as the pruning fraction is below a certain threshold, gradient descent can drive the training loss toward zero. More surprisingly, the generalization bound gets better as the pruning fraction gets larger.
  arXiv  Detail & Related papers  (2023-01-01T03:10:45Z)
• Bridging the Gap Between Target Networks and Functional Regularization [61.051716530459586]
  We propose an explicit Functional Regularization that is a convex regularizer in function space and can easily be tuned. We analyze the convergence of our method theoretically and empirically demonstrate that replacing Target Networks with the more theoretically grounded Functional Regularization approach leads to better sample efficiency and performance improvements.
  arXiv  Detail & Related papers  (2022-10-21T22:27:07Z)
• Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learning [4.97235247328373]
  This work addresses meta-learning (ML) by considering deep networks with local winner-takes-all (LWTA) activations. This type of network units results in sparse representations from each model layer, as the units are organized into blocks where only one unit generates a non-zero output. Our approach produces state-of-the-art predictive accuracy on few-shot image classification and regression experiments, as well as reduced predictive error on an active learning setting.
  arXiv  Detail & Related papers  (2022-08-02T16:19:54Z)
• Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness [15.395021925719817]
  Batch normalization (BN) is a technique for training deep neural networks that accelerates their convergence to reach higher accuracy. We show that BN incentivizes the model to rely on low-variance features that are highly specific to the training (in-domain) data. We propose Counterbalancing Teacher (CT) to enforce the student network's learning of robust representations.
  arXiv  Detail & Related papers  (2022-07-04T16:16:24Z)
• Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization [52.7137956951533]
  We argue that devising simpler methods for learning predictors on existing features is a promising direction for future research. We introduce Domain-Adjusted Regression (DARE), a convex objective for learning a linear predictor that is provably robust under a new model of distribution shift. Under a natural model, we prove that the DARE solution is the minimax-optimal predictor for a constrained set of test distributions.
  arXiv  Detail & Related papers  (2022-02-14T16:42:16Z)
• Self-Ensembling GAN for Cross-Domain Semantic Segmentation [107.27377745720243]
  This paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN. Despite its simplicity, we find SE-GAN can significantly boost the performance of adversarial training and enhance the stability of the model.
  arXiv  Detail & Related papers  (2021-12-15T09:50:25Z)
• Hindsight Network Credit Assignment [1.370633147306388]
  We present Hindsight Network Credit Assignment (HNCA), a novel learning method for neural networks. HNCA works by assigning credit to each neuron's output based on how it influences the output of its immediate children in the network.
  arXiv  Detail & Related papers  (2020-11-24T20:16:45Z)
• Learning by Competition of Self-Interested Reinforcement Learning Agents [0.0]
  An artificial neural network can be trained by uniformly broadcasting a reward signal to units that implement a REINFORCE learning rule. We propose replacing the reward signal to hidden units with the change in the $L2$ norm of the unit's outgoing weight. Our experiments show that a network trained with Weight Maximization can learn significantly faster than REINFORCE and slightly slower than backpropagation.
  arXiv  Detail & Related papers  (2020-10-19T18:18:53Z)
• Self-Supervised Dynamic Networks for Covariate Shift Robustness [9.542023122304098]
  Self-Supervised Dynamic Networks (SSDN) is an input-dependent mechanism that allows a self-supervised network to predict the weights of the main network. We present the conceptual and empirical advantages of the proposed method on the problem of image classification.
  arXiv  Detail & Related papers  (2020-06-06T19:37:20Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)

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.