No More Adam: Learning Rate Scaling at Initialization is All You Need

• URL: http://arxiv.org/abs/2412.11768v2
• Date: Tue, 17 Dec 2024 09:30:44 GMT
• Title: No More Adam: Learning Rate Scaling at Initialization is All You Need
• Authors: Minghao Xu, Lichuan Xiang, Xu Cai, Hongkai Wen,
• Abstract summary: SGD-SaI is a simple yet effective enhancement to gradient descent with momentum (SGDM) By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first. Despite its simplicity and efficiency, SGD-SaI consistently matches or outperforms AdamW in training a variety of Transformer-based tasks.
• Score: 13.892699813809857
• License:
• Abstract: In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplicity and efficiency, SGD-SaI consistently matches or outperforms AdamW in training a variety of Transformer-based tasks, effectively overcoming a long-standing challenge of using SGD for training Transformers. SGD-SaI excels in ImageNet-1K classification with Vision Transformers(ViT) and GPT-2 pretraining for large language models (LLMs, transformer decoder-only), demonstrating robustness to hyperparameter variations and practicality for diverse applications. We further tested its robustness on tasks like LoRA fine-tuning for LLMs and diffusion models, where it consistently outperforms state-of-the-art optimizers. From a memory efficiency perspective, SGD-SaI achieves substantial memory savings for optimizer states, reducing memory usage by 5.93 GB for GPT-2 (1.5B parameters) and 25.15 GB for Llama2-7B compared to AdamW in full-precision training settings.

Related papers

• Gradient Multi-Normalization for Stateless and Scalable LLM Training [16.037614012166063]
  Training large language models (LLMs) typically relies on adaptives like Adam which store additional state information to accelerate convergence but incur significant memory overhead. Recent efforts, such as SWAN (Ma et al., 2024) address this by eliminating the need for states while achieving performance comparable to Adam via a multi-step preprocessing procedure applied to instantaneous gradients. We introduce a novel framework for designing stateless gradients that normalizes gradients according to multiple norms. Experiments on pre-training LLaMA models with up to 1 billion parameters demonstrate a 3X speedup over Adam with significantly reduced memory requirements, outperforming other memory-efficient baseline
  arXiv  Detail & Related papers  (2025-02-10T18:09:53Z)
• APOLLO: SGD-like Memory, AdamW-level Performance [61.53444035835778]
  Large language models (LLMs) are notoriously memory-intensive during training. Various memory-efficient Scals have been proposed to reduce memory usage. They face critical challenges: (i) costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial memory overhead to maintain competitive performance.
  arXiv  Detail & Related papers  (2024-12-06T18:55:34Z)
• Gated Slot Attention for Efficient Linear-Time Sequence Modeling [59.019501274074564]
  Gated Slot Attention (GSA) enhances Attention with Bounded-memory-Control (ABC) GSA incorporates a gating mechanism inspired by Gated Linear Attention (GLA)
  arXiv  Detail & Related papers  (2024-09-11T09:49:50Z)
• Efficient Language Model Architectures for Differentially Private Federated Learning [21.280600854272716]
  Cross-device federated learning (FL) is a technique that trains a model on data distributed across typically millions of edge devices without data leaving the devices. In centralized training of language models, adaptives are preferred as they offer improved stability and performance. We propose a scale-in Coupled Input Forget Gate (SI CIFG) recurrent network by modifying the sigmoid and tanh activations in neural recurrent cell.
  arXiv  Detail & Related papers  (2024-03-12T22:21:48Z)
• AdaLomo: Low-memory Optimization with Adaptive Learning Rate [59.64965955386855]
  We introduce low-memory optimization with adaptive learning rate (AdaLomo) for large language models. AdaLomo results on par with AdamW, while significantly reducing memory requirements, thereby lowering the hardware barrier to training large language models.
  arXiv  Detail & Related papers  (2023-10-16T09:04:28Z)
• CAME: Confidence-guided Adaptive Memory Efficient Optimization [20.009302737137787]
  Adaptive gradient methods have demonstrated excellent performance in the training of large language models. The need for maintaining second-moment estimates requires maintaining a high cost of extra memory overheads. Several memory-efficients have been proposed to obtain a drastic reduction in auxiliary memory usage, but with a performance penalty. We propose CAME to simultaneously achieve two goals: fast convergence as in traditional adaptive methods, and low memory usage as in memory-efficient methods.
  arXiv  Detail & Related papers  (2023-07-05T06:05:36Z)
• Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model [89.8764435351222]
  We propose a new family of unbiased estimators called WTA-CRS, for matrix production with reduced variance. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones.
  arXiv  Detail & Related papers  (2023-05-24T15:52:08Z)
• On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance [2.71467552808655]
  We exploit the layerwise statistics to suppress the range of the adaptive stepsizes of Adam. The resulting algorithm is referred to as SET-Adam, where SET is a brief notation of the three operations. SET-Adam produces higher validation accuracies than Adam and AdaBelief for training ResNet18 over ImageNet.
  arXiv  Detail & Related papers  (2023-02-02T11:46:23Z)
• Robust Training of Neural Networks using Scale Invariant Architectures [70.67803417918854]
  In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks. We show that this general approach is robust to rescaling of parameter and loss. We design a scale invariant version of BERT, called SIBERT, which when trained simply by vanilla SGD achieves performance comparable to BERT trained by adaptive methods like Adam.
  arXiv  Detail & Related papers  (2022-02-02T11:58:56Z)
• Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
  We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem) AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient. Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
  arXiv  Detail & Related papers  (2020-10-21T14:49:00Z)

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.