Pith. sign in

REVIEW 5 cited by

mathbb{R}^(2k) is Theoretically Large Enough for Embedding-based Top-k Retrieval

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 2601.20844 v3 pith:G5VSMIE4 submitted 2026-01-28 cs.LG cs.AIcs.IR

mathbb{R}^(2k) is Theoretically Large Enough for Embedding-based Top-k Retrieval

classification cs.LG cs.AIcs.IR
keywords retrievalcentroiddimensionembedding-basedepsilonrobustsqrttheoretical
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper studies the Minimal Embeddable Dimension (MED): the least dimension in which there exists a configuration of $m$ object vectors so that every subset of size at most $k$ is exactly retrieved by score comparison. Our result shows MED is $\Theta(k)$, independent of $m$, for inner product, Euclidean distance, and cosine similarity. We then consider Robust MED (RMED), where all vectors are unit normed and an $\epsilon$ gap of scores is required. We derive the $m$-dependent feasibility ceiling $\epsilon_\star(m,k)=m/\sqrt{k(m-1)(m-k)}$, which approaches $1/\sqrt{k}$ when $m\gg k$, and a Gaussian centroid construction gives a robust witness upper bound in the feasible margin regime. Numerical simulation on synthetic top-$2$ retrieval with cyclic polytope and centroid query optimization confirmed our theoretical claims. Experiments on LIMIT and LIMIT-small datasets also show that simple embedding-based retrieval baselines can overfit and outperform the reported single-vector LLM embedding baseline. Both theoretical and empirical findings rule out the lack of exact geometric capacity as the obstruction.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Compact Geometric Representations of Hierarchies

    stat.ML 2026-06 unverdicted novelty 8.0

    Proves constant-dimension 3 reachability embeddings for directed trees, O(t log n) for treewidth-t graphs, with lower bounds of Omega(n) for general DAGs and Omega(t/log(n/t)) for treewidth t, plus real-dataset results.

  2. What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study

    cs.IR 2026-06 unverdicted novelty 8.0

    Quantization forces Bd = Ω(k ln N) for perfect top-k retrieval realizability, plus a B* = O(ln ln N) threshold below which no d works under uniform scalar quantization.

  3. Is Dimensionality a Barrier for Retrieval Models?

    cs.LG 2026-05 unverdicted novelty 8.0

    Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse que...

  4. Non-negative Elastic Net Decoding for Information Retrieval

    cs.IR 2026-06 unverdicted novelty 7.0

    NNN decoding selects documents via non-negative elastic net reconstruction of the query embedding, with a theorem showing it strictly dominates dense retrieval on correlated corpora and experiments showing gains over ...

  5. Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables

    cs.AI 2026-05 unverdicted novelty 7.0

    NS3 approximates joint ranking for EFO_k queries on KGs by merging free variables into hypernodes, pruning domains with dynamic budget B, and reducing to EFO_{k-1} queries, improving joint performance on three dataset...