LASER: Attention with Exponential Transformation

• URL: http://arxiv.org/abs/2411.03493v2
• Date: Sun, 13 Jul 2025 21:20:50 GMT
• Title: LASER: Attention with Exponential Transformation
• Authors: Sai Surya Duvvuri, Inderjit S. Dhillon,
• Abstract summary: We analyze the gradients backpropagated through the softmax operation in the attention mechanism and observe that these gradients can often be small.<n>We introduce a new attention mechanism called LASER, which we analytically show to admit a larger gradient signal.<n>We show that LASER attention can be implemented by making small modifications to existing attention implementations.
• Score: 20.1832156343096
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's performance. We analyze the gradients backpropagated through the softmax operation in the attention mechanism and observe that these gradients can often be small. This poor gradient signal backpropagation can lead to inefficient learning of parameters preceeding the attention operations. To this end, we introduce a new attention mechanism called LASER, which we analytically show to admit a larger gradient signal. We show that LASER attention can be implemented by making small modifications to existing attention implementations. We conduct experiments on autoregressive large language models (LLMs) with upto 7.7 billion parameters with an average improvement of upto 1.44% over standard attention on downstream evaluations and 1.65% finetuning improvements. Additionally, LASER demonstrates generalization performance improvement across a variety of tasks (vision, text and speech):Vision Transformer (ViT) on Imagenet, Conformer on the Librispeech speech-to-text and BERT with 2.2 billion parameters.

Related papers

• DiffLoRA: Differential Low-Rank Adapters for Large Language Models [59.58987161199141]
  We introduce DiffLoRA, a parameter-efficient adaptation of the differential attention mechanism, with low-rank adapters on both positive and negative attention terms.<n>We evaluate DiffLoRA across a broad range of NLP tasks, including general benchmarks, many-shot in-context learning, RAG, and long-context tests.
  arXiv  Detail & Related papers  (2025-07-31T14:24:59Z)
• Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement [13.38679135071682]
  We propose a Function-preserving Attention Replacement framework that replaces all attention blocks in pretrained transformers with learnable sequence-to-sequence modules.<n>We validate FAR on the DeiT vision transformer family and demonstrate that it matches the accuracy of the original models on ImageNet and multiple downstream tasks with reduced parameters and latency.
  arXiv  Detail & Related papers  (2025-05-24T02:23:46Z)
• Transformer Meets Twicing: Harnessing Unattended Residual Information [2.1605931466490795]
  Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism has proven capable of handling complex data patterns, it has been observed that the representational capacity of the attention matrix degrades significantly across transformer layers. We propose the Twicing Attention, a novel attention mechanism that uses kernel twicing procedure in nonparametric regression to alleviate the low-pass behavior of associated NLM smoothing.
  arXiv  Detail & Related papers  (2025-03-02T01:56:35Z)
• Breaking the Low-Rank Dilemma of Linear Attention [61.55583836370135]
  Linear attention provides a far more efficient solution by reducing the complexity to linear levels. Our experiments indicate that this performance drop is due to the low-rank nature of linear attention's feature map. We introduce Rank-Augmented Linear Attention (RALA), which rivals the performance of Softmax attention while maintaining linear complexity and high efficiency.
  arXiv  Detail & Related papers  (2024-11-12T08:30:59Z)
• ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers [7.155242379236052]
  Quantization of Vision Transformers (ViTs) has emerged as a promising solution to mitigate these challenges. Existing methods still suffer from significant accuracy loss at low-bit. ADFQ-ViT provides significant improvements over various baselines in image classification, object detection, and instance segmentation tasks at 4-bit.
  arXiv  Detail & Related papers  (2024-07-03T02:41:59Z)
• FAST: Factorizable Attention for Speeding up Transformers [1.3637227185793512]
  We present a linearly scaled attention mechanism that maintains the full representation of the attention matrix without compromising on sparsification. Results indicate that our attention mechanism has a robust performance and holds significant promise for diverse applications where self-attention is used.
  arXiv  Detail & Related papers  (2024-02-12T18:59:39Z)
• FLatten Transformer: Vision Transformer using Focused Linear Attention [80.61335173752146]
  Linear attention offers a much more efficient alternative with its linear complexity. Current linear attention approaches either suffer from significant performance degradation or introduce additional computation overhead. We propose a novel Focused Linear Attention module to achieve both high efficiency and expressiveness.
  arXiv  Detail & Related papers  (2023-08-01T10:37:12Z)
• Towards Accurate Post-Training Quantization for Vision Transformer [48.779346466374406]
  Existing post-training quantization methods still cause severe performance drops. APQ-ViT surpasses the existing post-training quantization methods by convincing margins.
  arXiv  Detail & Related papers  (2023-03-25T03:05:26Z)
• Skip-Attention: Improving Vision Transformers by Paying Less Attention [55.47058516775423]
  Vision computation transformers (ViTs) use expensive self-attention operations in every layer. We propose SkipAt, a method to reuse self-attention from preceding layers to approximate attention at one or more subsequent layers. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS.
  arXiv  Detail & Related papers  (2023-01-05T18:59:52Z)
• A Close Look at Spatial Modeling: From Attention to Convolution [70.5571582194057]
  Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. We generalize self-attention formulation to abstract a queryirrelevant global context directly and integrate the global context into convolutions. With less than 14M parameters, our FCViT-S12 outperforms related work ResT-Lite by 3.7% top1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-12-23T19:13:43Z)
• ViT-LSLA: Vision Transformer with Light Self-Limited-Attention [4.903718320156974]
  This paper presents a light self-limited-attention (LSLA) consisting of a light self-attention mechanism (LSA) to save the computation cost and the number of parameters, and a self-limited-attention mechanism (SLA) to improve the performance. experiments show that ViT-LSLA achieves 71.6% top-1 accuracy on IP102; 87.2% top-1 accuracy on Mini-ImageNet.
  arXiv  Detail & Related papers  (2022-10-31T07:46:45Z)
• The Devil in Linear Transformer [42.232886799710215]
  Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. They usually suffer from degraded performances on various tasks and corpus. In this paper, we identify two key issues that lead to such performance gaps.
  arXiv  Detail & Related papers  (2022-10-19T07:15:35Z)
• The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers [59.87030906486969]
  This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. We show that sparsity is a prevalent phenomenon that occurs for both natural language processing and vision tasks. We discuss how sparsity immediately implies a way to significantly reduce the FLOP count and improve efficiency for Transformers.
  arXiv  Detail & Related papers  (2022-10-12T15:25:19Z)
• Vicinity Vision Transformer [53.43198716947792]
  We present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.
  arXiv  Detail & Related papers  (2022-06-21T17:33:53Z)
• ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention [48.697458429460184]
  Two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer. This paper proposes a well-designed model named ERNIE-Sparse. It consists of two distinctive parts: (i) Hierarchical Sparse Transformer (HST) to sequentially unify local and global information, and (ii) Self-Attention Regularization (SAR) to minimize the distance for transformers with different attention topologies.
  arXiv  Detail & Related papers  (2022-03-23T08:47:01Z)
• An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition [28.06475768075206]
  Non-autoregressive mechanisms can significantly decrease inference time for speech transformers. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT) has shown a large real time factor (RTF) improvement over autoregressive transformers (AT) We propose several methods to improve the accuracy of the end-to-end CASS-NAT, followed by performance analyses.
  arXiv  Detail & Related papers  (2021-06-18T02:58:30Z)

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.