AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

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

Zihao Wang, Hang Yin, Lihui Liu, Hanghang Tong, Yangqiu Song, Ginny Wong, Simon See

ICML 2026 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace learned single-vector embedder with random token-sum (vanilla tokenizer)random Gaussian token vectors · LIMIT (d=4096)Recall@2: 0.030 -> 0.7060Improved
replace learned single-vector embedder with random token-sum (vanilla tokenizer)random Gaussian token vectors · LIMIT-small (d=4096)Recall@2: 0.543 -> 0.9545Improved
use handmade phrase tokenizer instead of Qwen tokenizer (ablation)random token-sum · LIMIT (d=4096)Recall@2: 0.2675 -> 0.9980Improved
use Qwen3-0.6B tokenizer instead of vanilla word tokenizer (ablation)random token-sum · LIMIT (d=4096)Recall@2: 0.7060 -> 0.2675Hurt
increase embedding dimension from 32 to 4096 (ablation)random token-sum, handmade tokenizer · LIMITRecall@2: 0.0020 -> 0.9980Improved
use cyclic polytope construction for top-2 retrievalcyclic-polytope witness · synthetic top-2 retrievalwitness dimension: dimension 4 for every tested mImproved
use centroid-query gradient descent instead of fitted free-embedding curvecentroid GD witness · synthetic top-2 retrievalwitness dimensionImproved
use cyclic polytope to overfit LIMIT in R4cyclic polytope · LIMIT and LIMIT-smallexact top-2 retrievalImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy