相关论文: KDEformer: Accelerating Transformers via Kernel De…

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…

In the kernel density estimation (KDE) problem, we are given a set $X$ of data points in $\mathbb{R}^d$, a kernel function $k: \mathbb{R}^d \times \mathbb{R}^d \rightarrow \mathbb{R}$, and a query point $\mathbf{q} \in \mathbb{R}^d$, and…

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Multi-scale deformable attention (MSDeformAttn) has emerged as a key mechanism in various vision tasks, demonstrating explicit superiority attributed to multi-scale grid-sampling. However, this newly introduced operator incurs irregular…

Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work, we study how to improve the learning of scaled dot-product…

In deep learning theory, the covariance matrix of the representations serves as a proxy to examine the network's trainability. Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention…

The performance of multivariate kernel density estimation (KDE) depends strongly on the choice of bandwidth matrix. The high computational cost required for its estimation provides a big motivation to develop fast and accurate methods. One…

Despite their power, Transformers face challenges with long sequences due to the quadratic complexity of self-attention. To address this limitation, methods like $k$-Nearest-Neighbor ($k$NN) attention have been introduced [Roy, Saffar,…

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Random feature attention (RFA) adopts random fourier feature (RFF) methods to approximate the softmax function, resulting in a linear time and space attention mechanism that enables the construction of an efficient Transformer. Inspired by…

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to quadratic time and memory…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often face significant computational bottlenecks, particularly in…

Score-debiased kernel density estimation (SD-KDE) achieves improved asymptotic convergence rates over classical KDE, but its use of an empirical score has made it significantly slower in practice. We show that by re-ordering the SD-KDE…

In the current landscape of large models, the Transformer stands as a cornerstone, playing a pivotal role in shaping the trajectory of modern models. However, its application encounters challenges attributed to the substantial computational…

Autoregressive Transformers are strong language models but incur O(T) complexity during per-token generation due to the self-attention mechanism. Recent work proposes kernel-based methods to approximate causal self-attention by replacing it…

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…