Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.04397 v1 pith:DNWM5HCD submitted 2023-04-10 cs.DS cs.LG

classification cs.DScs.LG
keywords matrixattentiondenoteomegadimensionllmsmathrmalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Universal Approximation of Visual Autoregressive Transformers

    cs.LG 2025-02 reject novelty 4.0 of 10

    The paper's headline claim that VAR transformers universally approximate all Lipschitz image maps is not supported, because the theorem restricts the target class and its key lemma has an invalid linearity step.

Pith tools