An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

• URL: http://arxiv.org/abs/2007.06049v2
• Date: Thu, 22 Oct 2020 16:36:44 GMT
• Title: An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay
• Authors: Scott Fujimoto, David Meger, Doina Precup
• Abstract summary: We show that any loss function evaluated with non-uniformly sampled data can be transformed into another uniformly sampled loss function. Surprisingly, we find in some environments PER can be replaced entirely by this new loss function without impact to empirical performance.
• Score: 72.23433407017558
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error. We show that any loss function evaluated with non-uniformly sampled data can be transformed into another uniformly sampled loss function with the same expected gradient. Surprisingly, we find in some environments PER can be replaced entirely by this new loss function without impact to empirical performance. Furthermore, this relationship suggests a new branch of improvements to PER by correcting its uniformly sampled loss function equivalent. We demonstrate the effectiveness of our proposed modifications to PER and the equivalent loss function in several MuJoCo and Atari environments.

Related papers

• Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes [0.0]
  We theoretically analyze the convergence of the loss landscape in a fully connected neural network and derive upper bounds for the difference in loss function values when adding a new object to the sample. Our empirical study confirms these results on various datasets, demonstrating the convergence of the loss function surface for image classification tasks.
  arXiv  Detail & Related papers  (2024-09-18T14:04:15Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Alternate Loss Functions for Classification and Robust Regression Can Improve the Accuracy of Artificial Neural Networks [6.452225158891343]
  This paper shows that training speed and final accuracy of neural networks can significantly depend on the loss function used to train neural networks. Two new classification loss functions that significantly improve performance on a wide variety of benchmark tasks are proposed.
  arXiv  Detail & Related papers  (2023-03-17T12:52:06Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Learning Compact Features via In-Training Representation Alignment [19.273120635948363]
  In each epoch, the true gradient of the loss function is estimated using a mini-batch sampled from the training set. We propose In-Training Representation Alignment (ITRA) that explicitly aligns feature distributions of two different mini-batches with a matching loss. We also provide a rigorous analysis of the desirable effects of the matching loss on feature representation learning.
  arXiv  Detail & Related papers  (2022-11-23T22:23:22Z)
• A Fair Loss Function for Network Pruning [70.35230425589592]
  We introduce the performance weighted loss function, a simple modified cross-entropy loss function that can be used to limit the introduction of biases during pruning. Experiments using the CelebA, Fitzpatrick17k and CIFAR-10 datasets demonstrate that the proposed method is a simple and effective tool.
  arXiv  Detail & Related papers  (2022-11-18T15:17:28Z)
• The Fisher-Rao Loss for Learning under Label Noise [9.238700679836855]
  We study the Fisher-Rao loss function, which emerges from the Fisher-Rao distance in the statistical manifold of discrete distributions. We derive an upper bound for the performance degradation in the presence of label noise, and analyse the learning speed of this loss.
  arXiv  Detail & Related papers  (2022-10-28T20:50:10Z)
• Center Prediction Loss for Re-identification [65.58923413172886]
  We propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples. We show that this new loss leads to a more flexible intra-class distribution constraint while ensuring the between-class samples are well-separated.
  arXiv  Detail & Related papers  (2021-04-30T03:57:31Z)
• Reducing Representation Drift in Online Continual Learning [87.71558506591937]
  We study the online continual learning paradigm, where agents must learn from a changing distribution with constrained memory and compute. In this work we instead focus on the change in representations of previously observed data due to the introduction of previously unobserved class samples in the incoming data stream.
  arXiv  Detail & Related papers  (2021-04-11T15:19:30Z)

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.