Promoting Exploration in Memory-Augmented Adam using Critical Momenta

• URL: http://arxiv.org/abs/2307.09638v2
• Date: Mon, 17 Jun 2024 19:47:35 GMT
• Title: Promoting Exploration in Memory-Augmented Adam using Critical Momenta
• Authors: Pranshu Malviya, Gonçalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chandar,
• Abstract summary: We propose a memory-augmented version of Adam that encourages exploration towards flatter minima. This buffer prompts the model to overshoot beyond narrow minima, promoting exploration. We empirically demonstrate that it can improve model performance for image classification on ImageNet and CIFAR10/100, language modelling on Penn Treebank, and online learning tasks on TinyImageNet and 5-dataset.
• Score: 33.62231951499847
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergence and robustness to hyperparameter settings. However, they often struggle with generalization, attributed to their tendency to converge to sharp minima in the loss landscape. To address this, we propose a new memory-augmented version of Adam that encourages exploration towards flatter minima by incorporating a buffer of critical momentum terms during training. This buffer prompts the optimizer to overshoot beyond narrow minima, promoting exploration. Through comprehensive analysis in simple settings, we illustrate the efficacy of our approach in increasing exploration and bias towards flatter minima. We empirically demonstrate that it can improve model performance for image classification on ImageNet and CIFAR10/100, language modelling on Penn Treebank, and online learning tasks on TinyImageNet and 5-dataset. Our code is available at \url{https://github.com/chandar-lab/CMOptimizer}.

Related papers

• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• Bilevel Fast Scene Adaptation for Low-Light Image Enhancement [50.639332885989255]
  Enhancing images in low-light scenes is a challenging but widely concerned task in the computer vision. Main obstacle lies in the modeling conundrum from distribution discrepancy across different scenes. We introduce the bilevel paradigm to model the above latent correspondence. A bilevel learning framework is constructed to endow the scene-irrelevant generality of the encoder towards diverse scenes.
  arXiv  Detail & Related papers  (2023-06-02T08:16:21Z)
• Scaling Laws For Deep Learning Based Image Reconstruction [26.808569077500128]
  We study whether major performance gains are expected from scaling up the training set size. An initially steep power-law scaling slows significantly already at moderate training set sizes. We analytically characterize the performance of a linear estimator learned with early stopped gradient descent.
  arXiv  Detail & Related papers  (2022-09-27T14:44:57Z)
• Core Risk Minimization using Salient ImageNet [53.616101711801484]
  We introduce the Salient Imagenet dataset with more than 1 million soft masks localizing core and spurious features for all 1000 Imagenet classes. Using this dataset, we first evaluate the reliance of several Imagenet pretrained models (42 total) on spurious features. Next, we introduce a new learning paradigm called Core Risk Minimization (CoRM) whose objective ensures that the model predicts a class using its core features.
  arXiv  Detail & Related papers  (2022-03-28T01:53:34Z)
• Memory-Augmented Reinforcement Learning for Image-Goal Navigation [67.3963444878746]
  We present a novel method that leverages a cross-episode memory to learn to navigate. In order to avoid overfitting, we propose to use data augmentation on the RGB input during training. We obtain this competitive performance from RGB input only, without access to additional sensors such as position or depth.
  arXiv  Detail & Related papers  (2021-01-13T16:30:20Z)
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation [49.90178055521207]
  This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes.
  arXiv  Detail & Related papers  (2020-12-09T12:40:13Z)
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach [27.350615059290348]
  We propose a meta-learning approach with complemented representations network (MCRNet) for few-shot image classification. In particular, we embed a latent space, where latent codes are reconstructed with extra representation information to complement the representation deficiency. Our end-to-end framework achieves the state-of-the-art performance in image classification on three standard few-shot learning datasets.
  arXiv  Detail & Related papers  (2020-07-21T13:25:54Z)
• Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy [21.89072742618842]
  We provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We propose CutBlur that cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. Our method consistently and significantly improves the performance across various scenarios.
  arXiv  Detail & Related papers  (2020-04-01T13:49:38Z)

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.