cs.CGJan 4, 2026

Exact and Approximate Range Queries in Ball Mapper

Authors: Jay-Anne BulauanJohn Rick Manzanares

Abstract

Ball Mapper summarizes a finite metric dataset by covering the sample with closed balls centered at selected landmarks and connecting landmarks whose balls share observations. Its construction therefore depends critically on repeated fixed radius range queries, yet the effect of replacing exact queries by approximate search has not been systematically characterized. We formulate Ball Mapper through an abstract range query procedure that separates the mathematical construction from the search backend used to realize it. Under fixed ordering, exact procedures preserve the landmark sequence, cover, graph, and membership-based colorings. For approximate procedures, we derive deterministic bounds on covering radius and landmark separation under additive and multiplicative query errors, prove inclusions for the induced nerve, characterize edge survival through witness redundancy for conservative approximations, and bound perturbations of mean vertex colorings. The accompanying implementation provides independent exact reference backends together with exhaustive and approximate search methods under a common closed ball convention. Experiments on Gaussian, mixture, and noisy curve data across three seeds show that approximation fidelity depends strongly on geometry and that edges supported by multiple witnesses are substantially more robust to missed memberships. At 20,000 observations, the approximate indexes did not outperform exhaustive FAISS Flat search. The results therefore establish a framework for controlled approximation rather than a universal speed advantage, and identify the geometric and combinatorial quantities that govern when approximate range search preserves the Ball Mapper summary.

Explore similar work

Apr 22, 2026cs.IR

Semantic Recall for Vector Search

We introduce Semantic Recall, a novel metric to assess the quality of approximate nearest neighbor search algorithms by considering only semantically relevant objects that are theoretically retrievable via exact nearest neighbor search. Unlike traditional recall, semantic recall does not penalize algorithms for failing to retrieve objects that are semantically irrelevant to the query, even if those objects are among their nearest neighbors. We demonstrate that semantic recall is particularly useful for assessing retrieval quality on queries that have few relevant results among their nearest neighbors-a scenario we uncover to be common within embedding datasets. Additionally, we introduce Tolerant Recall, a proxy metric that approximates semantic recall when semantically relevant objects cannot be identified. We empirically show that our metrics are more effective indicators of retrieval quality, and that optimizing search algorithms for these metrics can lead to improved cost-quality tradeoffs.
Leonardo Kuffo, Ioanna Tsakalidou, Roberta De Viti +3
Oct 1, 2025cs.LG

Panorama: Fast-Track Nearest Neighbors

Approximate Nearest-Neighbor Search (ANNS) pipelines for high-dimensional neural embeddings spend the bulk of their query time in candidate verification, making it the primary bottleneck in the search process. In this paper, we present PANORAMA, a state-of-the-art refinement technique that accelerates verification by exploiting the inherent spectral decay of these embeddings. Using PCA to compact signal energy, PANORAMA evaluates candidate distances incrementally, computing at each step a strict lower bound on the full-vector distance and dynamically pruning candidates the moment this bound exceeds the running k-th nearest neighbor distance. While PCA's concentration of variance facilitates pruning, it breaks the uniform-variance assumption required by Product Quantization (PQ); we resolve this with a variance-shaping step that redistributes energy across subvectors, rendering accretive refinement compatible with quantized indexes. Optimized for modern memory hierarchies via vectorized bulk-pruning and cache-conscious data layouts, PANORAMA has been upstreamed into the FAISS library across major index families (IVFPQ/Flat, HNSW, and Refine). PANORAMA achieves higher QPS at any target recall with a cost that provably scales inversely with dataset spectral decay, delivering end-to-end speedups of up to 28.9x and outperforming probabilistic methods across all recall bands.
Vansh Ramani, Alexis Schlomer, Akash Nayar +3
May 2, 2026cs.DS

New Bounds for Kernel Sums via Fast Spherical Embeddings

We study query time bounds for the fundamental problem of estimating the kernel mean 1XxXk(x,y)\frac1{|X|}\sum_{x\in X}\mathbf{k}(x,y) of a query yy in a finite dataset XRdX\subset\mathbb{R}^d up to a prescribed additive error ε\varepsilon. The best known bounds for the Gaussian kernel are O(d/ε2)O(d/\varepsilon^2), O~(d+1/ε4)\widetilde O(d+1/\varepsilon^4), and O~(d+Δ2/ε2)\widetilde O(d+Δ^2/\varepsilon^2), where ΔΔ is the diameter of a region containing the points. We prove the new bound O~(d+εΔ2+1/ε3)\tilde O(d+\varepsilonΔ^2+1/\varepsilon^3), which improves over the previous ones in regimes with small error ε\varepsilon and intermediate diameter ΔΔ. At the center of our proof is a new fast spherical embedding theorem in the sense introduced by Bartal, Recht and Schulman (2011), which limits the embedded data diameter while preserving local Euclidean distances and avoiding ``distance collapse'' at larger scales. This fast embedding theorem may be of independent interest.
Tal Wagner