Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension

• URL: http://arxiv.org/abs/2304.04397v1
• Date: Mon, 10 Apr 2023 05:52:38 GMT
• Title: Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension
• Authors: Yichuan Deng, Sridhar Mahadevan, Zhao Song
• Abstract summary: We consider the sparsification of the attention problem. For any super large feature dimension, we can reduce it down to the size nearly linear in length of sentence.
• Score: 18.57735939471469
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) have shown their power in different areas. Attention computation, as an important subroutine of LLMs, has also attracted interests in theory. Recently the static computation and dynamic maintenance of attention matrix has been studied by [Alman and Song 2023] and [Brand, Song and Zhou 2023] from both algorithmic perspective and hardness perspective. In this work, we consider the sparsification of the attention problem. We make one simplification which is the logit matrix is symmetric. Let $n$ denote the length of sentence, let $d$ denote the embedding dimension. Given a matrix $X \in \mathbb{R}^{n \times d}$, suppose $d \gg n$ and $\| X X^\top \|_{\infty} < r$ with $r \in (0,0.1)$, then we aim for finding $Y \in \mathbb{R}^{n \times m}$ (where $m\ll d$) such that \begin{align*} \| D(Y)^{-1} \exp( Y Y^\top ) - D(X)^{-1} \exp( X X^\top) \|_{\infty} \leq O(r) \end{align*} We provide two results for this problem. $\bullet$ Our first result is a randomized algorithm. It runs in $\widetilde{O}(\mathrm{nnz}(X) + n^{\omega} ) $ time, has $1-\delta$ succeed probability, and chooses $m = O(n \log(n/\delta))$. Here $\mathrm{nnz}(X)$ denotes the number of non-zero entries in $X$. We use $\omega$ to denote the exponent of matrix multiplication. Currently $\omega \approx 2.373$. $\bullet$ Our second result is a deterministic algorithm. It runs in $\widetilde{O}(\min\{\sum_{i\in[d]}\mathrm{nnz}(X_i)^2, dn^{\omega-1}\} + n^{\omega+1})$ time and chooses $m = O(n)$. Here $X_i$ denote the $i$-th column of matrix $X$. Our main findings have the following implication for applied LLMs task: for any super large feature dimension, we can reduce it down to the size nearly linear in length of sentence.

Related papers

• The Communication Complexity of Approximating Matrix Rank [50.6867896228563]
  We show that this problem has randomized communication complexity $Omega(frac1kcdot n2log|mathbbF|)$. As an application, we obtain an $Omega(frac1kcdot n2log|mathbbF|)$ space lower bound for any streaming algorithm with $k$ passes.
  arXiv  Detail & Related papers  (2024-10-26T06:21:42Z)
• Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms [50.15964512954274]
  We study the problem of residual error estimation for matrix and vector norms using a linear sketch. We demonstrate that this gives a substantial advantage empirically, for roughly the same sketch size and accuracy as in previous work. We also show an $Omega(k2/pn1-2/p)$ lower bound for the sparse recovery problem, which is tight up to a $mathrmpoly(log n)$ factor.
  arXiv  Detail & Related papers  (2024-08-16T02:33:07Z)
• A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time [7.613259578185218]
  We focus on giving a provable guarantee for the one-layer attention network objective function $L(X,Y). In a multi-layer LLM network, the matrix $B in mathbbRn times d2$ can be viewed as the output of a layer. We provide an iterative algorithm to train loss function $L(X,Y)$ up $epsilon$ that runs in $widetildeO( (cal T_mathrmmat(n,d) + d
  arXiv  Detail & Related papers  (2023-09-14T04:23:40Z)
• Matrix Completion in Almost-Verification Time [37.61139884826181]
  We provide an algorithm which completes $mathbfM$ on $99%$ of rows and columns. We show how to boost this partial completion guarantee to a full matrix completion algorithm.
  arXiv  Detail & Related papers  (2023-08-07T15:24:49Z)
• Fast $(1+\varepsilon)$-Approximation Algorithms for Binary Matrix Factorization [54.29685789885059]
  We introduce efficient $(1+varepsilon)$-approximation algorithms for the binary matrix factorization (BMF) problem. The goal is to approximate $mathbfA$ as a product of low-rank factors. Our techniques generalize to other common variants of the BMF problem.
  arXiv  Detail & Related papers  (2023-06-02T18:55:27Z)
• Fast Attention Requires Bounded Entries [19.17278873525312]
  inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. We investigate whether faster algorithms are possible by implicitly making use of the matrix $A$. This gives a theoretical explanation for the phenomenon observed in practice that attention computation is much more efficient when the input matrices have smaller entries.
  arXiv  Detail & Related papers  (2023-02-26T02:42:39Z)
• A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee [16.409210914237086]
  Given a matrix $Ain mathbbRntimes d$ and a tensor $bin mathbbRn$, we consider the regression problem with $ell_infty$ guarantees. We show that in order to obtain such $ell_infty$ guarantee for $ell$ regression, one has to use sketching matrices that are dense. We also develop a novel analytical framework for $ell_infty$ guarantee regression that utilizes the Oblivious Coordinate-wise Embedding (OCE) property
  arXiv  Detail & Related papers  (2023-02-01T05:22:40Z)
• Sketching Algorithms and Lower Bounds for Ridge Regression [65.0720777731368]
  We give a sketching-based iterative algorithm that computes $1+varepsilon$ approximate solutions for the ridge regression problem. We also show that this algorithm can be used to give faster algorithms for kernel ridge regression.
  arXiv  Detail & Related papers  (2022-04-13T22:18:47Z)
• Learning a Latent Simplex in Input-Sparsity Time [58.30321592603066]
  We consider the problem of learning a latent $k$-vertex simplex $KsubsetmathbbRdtimes n$, given access to $AinmathbbRdtimes n$. We show that the dependence on $k$ in the running time is unnecessary given a natural assumption about the mass of the top $k$ singular values of $A$.
  arXiv  Detail & Related papers  (2021-05-17T16:40:48Z)
• The Average-Case Time Complexity of Certifying the Restricted Isometry Property [66.65353643599899]
  In compressed sensing, the restricted isometry property (RIP) on $M times N$ sensing matrices guarantees efficient reconstruction of sparse vectors. We investigate the exact average-case time complexity of certifying the RIP property for $Mtimes N$ matrices with i.i.d. $mathcalN(0,1/M)$ entries.
  arXiv  Detail & Related papers  (2020-05-22T16:55:01Z)

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.