Variational Learning is Effective for Large Deep Networks

• URL: http://arxiv.org/abs/2402.17641v2
• Date: Thu, 6 Jun 2024 04:31:43 GMT
• Title: Variational Learning is Effective for Large Deep Networks
• Authors: Yuesong Shen, Nico Daheim, Bai Cong, Peter Nickl, Gian Maria Marconi, Clement Bazan, Rio Yokota, Iryna Gurevych, Daniel Cremers, Mohammad Emtiyaz Khan, Thomas Möllenhoff,
• Abstract summary: We show that an Improved Variational Online Newton consistently matches or outperforms Adam for training large networks. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We find overwhelming evidence that variational learning is effective.
• Score: 76.94351631300788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for training large networks such as GPT-2 and ResNets from scratch. IVON's computational costs are nearly identical to Adam but its predictive uncertainty is better. We show several new use cases of IVON where we improve finetuning and model merging in Large Language Models, accurately predict generalization error, and faithfully estimate sensitivity to data. We find overwhelming evidence that variational learning is effective.

Related papers

• AdamL: A fast adaptive gradient method incorporating loss function [1.6025685183216696]
  We propose AdamL, a novel variant of the Adam, that takes into account the loss function information to attain better results. We show that AdamL achieves either the fastest convergence or the lowest objective function values when compared to Adam, EAdam, and AdaBelief. In the case of vanilla convolutional neural networks, AdamL stands out from the other Adam's variants and does not require the manual adjustment of the learning rate during the later stage of the training.
  arXiv  Detail & Related papers  (2023-12-23T16:32:29Z)
• Optimizing Dense Feed-Forward Neural Networks [0.0]
  We propose a novel feed-forward neural network constructing method based on pruning and transfer learning. Our approach can compress the number of parameters by more than 70%. We also evaluate the transfer learning level comparing the refined model and the original one training from scratch a neural network.
  arXiv  Detail & Related papers  (2023-12-16T23:23:16Z)
• Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs [9.010643838773477]
  We introduce a novel score for quantifying overfit, which monitors the forgetting rate of deep models on validation data. We show that overfit can occur with and without a decrease in validation accuracy, and may be more common than previously appreciated. We use our observations to construct a new ensemble method, based solely on the training history of a single network, which provides significant improvement without any additional cost in training time.
  arXiv  Detail & Related papers  (2023-10-17T09:22:22Z)
• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Sparsifying Bayesian neural networks with latent binary variables and normalizing flows [10.865434331546126]
  We will consider two extensions to the latent binary Bayesian neural networks (LBBNN) method. Firstly, by using the local reparametrization trick (LRT) to sample the hidden units directly, we get a more computationally efficient algorithm. More importantly, by using normalizing flows on the variational posterior distribution of the LBBNN parameters, the network learns a more flexible variational posterior distribution than the mean field Gaussian.
  arXiv  Detail & Related papers  (2023-05-05T09:40:28Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks [12.525959293825318]
  We introduce Learn, Unlearn, and Relearn (LURE) an online learning paradigm for deep neural networks (DNNs) LURE interchanges between the unlearning phase, which selectively forgets the undesirable information in the model, and the relearning phase, which emphasizes learning on generalizable features. We show that our training paradigm provides consistent performance gains across datasets in both classification and few-shot settings.
  arXiv  Detail & Related papers  (2023-03-18T16:45:54Z)
• How Do Adam and Training Strategies Help BNNs Optimization? [50.22482900678071]
  We show that Adam is better equipped to handle the rugged loss surface of BNNs and reaches a better optimum with higher generalization ability. We derive a simple training scheme, building on existing Adam-based optimization, which achieves 70.5% top-1 accuracy on the ImageNet dataset.
  arXiv  Detail & Related papers  (2021-06-21T17:59:51Z)
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration [74.5509794733707]
  We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution. Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs. Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
  arXiv  Detail & Related papers  (2021-02-17T18:59:28Z)
• The large learning rate phase of deep learning: the catapult mechanism [50.23041928811575]
  We present a class of neural networks with solvable training dynamics. We find good agreement between our model's predictions and training dynamics in realistic deep learning settings. We believe our results shed light on characteristics of models trained at different learning rates.
  arXiv  Detail & Related papers  (2020-03-04T17:52:48Z)

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.