Landscape-Aware Growing: The Power of a Little LAG

• URL: http://arxiv.org/abs/2406.02469v1
• Date: Tue, 4 Jun 2024 16:38:57 GMT
• Title: Landscape-Aware Growing: The Power of a Little LAG
• Authors: Stefani Karp, Nikunj Saunshi, Sobhan Miryoosefi, Sashank J. Reddi, Sanjiv Kumar,
• Abstract summary: We study the question of how to select the best growing strategy from a given pool of growing strategies. We present an alternative perspective based on early training dynamics, which we call "landscape-aware growing (LAG)"
• Score: 49.897766925371485
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, there has been increasing interest in efficient pretraining paradigms for training Transformer-based models. Several recent approaches use smaller models to initialize larger models in order to save computation (e.g., stacking and fusion). In this work, we study the fundamental question of how to select the best growing strategy from a given pool of growing strategies. Prior works have extensively focused on loss- and/or function-preserving behavior at initialization or simply performance at the end of training. Instead, we identify that behavior at initialization can be misleading as a predictor of final performance and present an alternative perspective based on early training dynamics, which we call "landscape-aware growing (LAG)". We perform extensive analysis of correlation of the final performance with performance in the initial steps of training and find early and more accurate predictions of the optimal growing strategy (i.e., with only a small "lag" after initialization). This perspective also motivates an adaptive strategy for gradual stacking.

Related papers

• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis [27.310894780313618]
  This paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. We confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints.
  arXiv  Detail & Related papers  (2024-04-01T16:00:01Z)
• An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning [36.619804184427245]
  Class-Incremental Learning (CIL) aims to build classification models from data streams. Due to catastrophic forgetting, CIL is particularly challenging when examples from past classes cannot be stored. Use of models pre-trained in a self-supervised way on large amounts of data has recently gained momentum.
  arXiv  Detail & Related papers  (2023-08-22T14:06:40Z)
• Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning [14.86600327306136]
  A general framework of unsupervised learning for optimization (CO) is to train a neural network (NN) whose output gives a problem solution by directly optimizing the CO objective. We propose a new objective of unsupervised learning for CO where the goal of learning is to search for good initialization for future problem instances rather than give direct solutions. We observe that even just the initial solution given by our model before fine-tuning can significantly outperform the baselines under various evaluation settings.
  arXiv  Detail & Related papers  (2023-01-08T22:14:59Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients [36.078414964088196]
  Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network. Current methods are insufficient to enable this optimization and lead to a large degradation in model performance. We propose Prospect Pruning (ProsPr), which uses meta-gradients through the first few steps of optimization to determine which weights to prune. Our method achieves state-of-the-art pruning performance on a variety of vision classification tasks, with less data and in a single shot compared to existing pruning-at-initialization methods.
  arXiv  Detail & Related papers  (2022-02-16T15:18:55Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Dynamic Scale Training for Object Detection [111.33112051962514]
  We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Experimental results demonstrate the efficacy of our proposed DST towards scale variation handling. It does not introduce inference overhead and could serve as a free lunch for general detection configurations.
  arXiv  Detail & Related papers  (2020-04-26T16:48:17Z)

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.