Is Dimensionality a Barrier for Retrieval Models?

• URL: http://arxiv.org/abs/2605.23556v1
• Date: Fri, 22 May 2026 12:22:20 GMT
• Title: Is Dimensionality a Barrier for Retrieval Models?
• Abstract summary: We show that the best possible margin without a restriction on the dimension, $mathsfmmathsfrd(+infty, A)-2log n)$ can be nearly achieved in dimension $d = O(mathsfmmathsfrd(+infty, A)-2log n)$.<n>Our main theorem establishes that the best possible margin without a restriction on the dimension, $mathsfmmathsfrd(+infty, A)-2log n)$ can be
• Score: 21.1705493494434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Why does the low dimensionality of representations, typically $d\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin embeddings in the following retrieval model, classically studied in communication complexity [PS86] and more recently in embedding-based retrieval [WBNL26]. Let $A\in \{0,1\}^{N\times n}$ be a matrix indicating whether each of $N$ queries is relevant to each of $n$ documents. We are interested in the largest margin $m>0,$ denoted by $\mathsf{m}^{\mathsf{rd}}(d, A),$ for which there exist unit norm embeddings of the queries and documents $\{U_j\}_{j = 1}^N, \{V_i\}_{i = 1}^n$ with the following property. $\langle U_j, V_i\rangle \ge m$ whenever $A_{ji} = 1$ and $\langle U_j, V_i\rangle \le -m$ otherwise. A large margin is a key proxy for representation quality: it controls both robustness to perturbations and compositional generalization across queries. Our main theorem establishes that the best possible margin without a restriction on the dimension, $\mathsf{m}^{\mathsf{rd}}(+\infty, A),$ can be nearly achieved in dimension $d = O(\mathsf{m}^{\mathsf{rd}}(+\infty, A)^{-2}\log n)$ which improves a theorem of [BDES02]. Together with a matching lower bound in Theorem 1.5, we conclude that when $A\in \{0,1\}^{\binom{n}{k}\times n}$ is the matrix containing all possible $k$-sparse rows once, dimension $d = O(k\log (n/k))$ is necessary and sufficient for the maximal possible margin $\mathsf{m}^{\mathsf{rd}}(+\infty, A) = Θ(k^{-1/2})$ in this setting. This fully resolves the setup of [WBNL26]. We also give several constructions for large margins when $d = o(k\log (n/k)).$ Finally, we empirically test the InfoNCE and sigmoid losses for producing large margin embeddings and demonstrate a clear advantage of the sigmoid loss.

Related papers

• A Simple Algorithm for Best Separable State [5.5559749120901385]
  We study the best separable state problem (BSS), which asks for the maximum acceptance probability of a quantum measurement over unentangled states.<n>In classical terms, the goal is to maximize $langle(x otimes y), M (x otimes y)rangle$ over unit vectors $x,y$ where $0 preceq M preceq I$.
  arXiv  Detail & Related papers  (2026-08-10T19:04:15Z)
• Near-Optimal Dimension Lower Bounds for Single-Vector Embeddings of Maximum Inner Product Similarity [75.14269295861845]
  For singleton queries, Chamfer becomes maximum inner product similarity (MAX-IP)<n>For every fixed $in(0,1)$, there are constants $A_,c_>0$.<n>Unit-sphere MAX-IP matrix is an exact two-valued affine image of the DNF pattern matrix with gap of at least $8$.
  arXiv  Detail & Related papers  (2026-07-22T17:27:20Z)
• Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors [3.9657575162895196]
  We give a proof of the conjecture of Nelson and Nguyen [FOCS 2013] on the optimal dimension and sparsity of oblivious subspace embeddings.<n>For any $ngeq d$ and $epsilongeq d-O(1)$, there is a random $tilde O(d/epsilon2)times n$ matrix $Pi$ with $tilde O(log(d)/epsilon)$ non-zeros per column such that for any $AinmathbbRntimes d
  arXiv  Detail & Related papers  (2025-08-19T19:45:52Z)
• 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)
• Optimal Embedding Dimension for Sparse Subspace Embeddings [4.042707434058959]
  A random $mtimes n$ matrix $S$ is an oblivious subspace embedding (OSE) We show that an $mtimes n$ random matrix $S$ with $mgeq (1+theta)d$ is an oblivious subspace embedding with $epsilon = O_theta(1)$. We use this to construct the first oblivious subspace embedding with $O(d)$ embedding dimension that can be applied faster than current matrix multiplication time.
  arXiv  Detail & Related papers  (2023-11-17T18:01:58Z)
• Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension [18.57735939471469]
  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.
  arXiv  Detail & Related papers  (2023-04-10T05:52:38Z)
• Low-degree learning and the metric entropy of polynomials [44.99833362998488]
  We prove that any (deterministic or randomized) algorithm which learns $mathscrF_nd$ with $L$-accuracy $varepsilon$ requires at least $Omega(sqrtvarepsilon)2dlog n leq log mathsfM(mathscrF_n,d,|cdot|_L,varepsilon) satisfies the two-sided estimate $$c (1-varepsilon)2dlog
  arXiv  Detail & Related papers  (2022-03-17T23:52:08Z)
• Low-Rank Approximation with $1/\epsilon^{1/3}$ Matrix-Vector Products [58.05771390012827]
  We study iterative methods based on Krylov subspaces for low-rank approximation under any Schatten-$p$ norm. Our main result is an algorithm that uses only $tildeO(k/sqrtepsilon)$ matrix-vector products.
  arXiv  Detail & Related papers  (2022-02-10T16:10:41Z)
• Threshold Phenomena in Learning Halfspaces with Massart Noise [56.01192577666607]
  We study the problem of PAC learning halfspaces on $mathbbRd$ with Massart noise under Gaussian marginals. Our results qualitatively characterize the complexity of learning halfspaces in the Massart model.
  arXiv  Detail & Related papers  (2021-08-19T16:16:48Z)
• Efficient Statistics for Sparse Graphical Models from Truncated Samples [19.205541380535397]
  We focus on two fundamental and classical problems: (i) inference of sparse Gaussian graphical models and (ii) support recovery of sparse linear models. For sparse linear regression, suppose samples $(bf x,y)$ are generated where $y = bf xtopOmega* + mathcalN(0,1)$ and $(bf x, y)$ is seen only if $y$ belongs to a truncation set $S subseteq mathbbRd$.
  arXiv  Detail & Related papers  (2020-06-17T09:21:00Z)
• 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.