# algorithms > Browse 17 items tagged with algorithms. ## Items - [Vector Index Types](https://vectordb.ever.works/ja/items/vector-index-types) — Different indexing strategies for vector databases including HNSW, IVF, LSH, and flat indexes. Each type offers different trade-offs between query speed, build time, accuracy, and memory usage. Understanding index types is crucial for optimizing vector database performance at scale. - [Breaking the Storage-Compute Bottleneck in Billion-Scale ANNS](https://vectordb.ever.works/ja/items/breaking-storage-compute-bottleneck) — A 2025 research paper presenting a GPU-driven asynchronous I/O framework for billion-scale approximate nearest neighbor search. The system addresses the fundamental bottleneck of data movement between storage and compute in large-scale vector search. - [Faster Maximum Inner Product Search in High Dimensions](https://vectordb.ever.works/ja/items/faster-mips-high-dimensions) — A 2022 research paper presenting algorithms for faster MIPS (Maximum Inner Product Search) in high-dimensional spaces. MIPS is crucial for recommendation systems, neural networks, and various machine learning applications. - [Graph-Based Algorithms for Diverse Similarity Search](https://vectordb.ever.works/ja/items/graph-based-diverse-similarity-search) — A 2026 research paper presenting graph-based algorithms for diverse similarity search, where results must be both similar to the query and diverse from each other. This addresses the common problem of redundant results in traditional similarity search. - [In-Place Updates of Graph Index](https://vectordb.ever.works/ja/items/in-place-updates-graph-index) — A 2026 research paper on streaming approximate nearest neighbor search with in-place graph index updates. The approach enables real-time index modifications without expensive rebuilds, crucial for dynamic datasets. - [JAG](https://vectordb.ever.works/ja/items/jag-joint-attribute-graphs) — Joint Attribute Graphs for Filtered Nearest Neighbor Search, a research paper that addresses the challenge of combining vector similarity search with attribute filtering. JAG presents a novel index structure that efficiently handles filtered ANN queries common in real-world applications. - [LLMs Meet Isolation Kernel](https://vectordb.ever.works/ja/items/llm-isolation-kernel-binary-embeddings) — A research paper introducing lightweight, learning-free binary embeddings for fast retrieval. The approach uses isolation kernels to generate binary embeddings that dramatically reduce storage requirements (32× compression) while maintaining retrieval quality. - [Maximum Inner Product is Query-Scaled Nearest Neighbor](https://vectordb.ever.works/ja/items/maximum-inner-product-query-scaled) — A theoretical paper establishing the relationship between Maximum Inner Product Search and query-scaled nearest neighbor search. This connection enables applying NN techniques to MIPS problems with theoretical guarantees. - [Monte Carlo Tree Search for Vector Indexing](https://vectordb.ever.works/ja/items/monte-carlo-tree-search-vectors) — Research on using Monte Carlo Tree Search algorithms for optimizing vector index construction and search strategies. Explores adaptive decision-making during graph building and query routing. - [OrchANN](https://vectordb.ever.works/ja/items/orchann-io-framework) — A unified I/O orchestration framework for skewed out-of-core vector search that addresses the challenge of billion-scale ANN search when the dataset exceeds available memory. OrchANN optimizes I/O operations for graph-based indexes stored on disk. - [PaCMAP](https://vectordb.ever.works/ja/items/pacmap-dimensionality-reduction) — Pairwise Controlled Manifold Approximation - a dimensionality reduction technique that preserves both local and global structure better than UMAP or t-SNE. Particularly effective for visualizing complex embedding spaces. - [PiPNN](https://vectordb.ever.works/ja/items/pipnn-ultra-scalable-indexing) — An ultra-scalable graph-based nearest neighbor indexing algorithm that builds state-of-the-art indexes up to 11.6× faster than Vamana (DiskANN) and 12.9× faster than HNSW. PiPNN uses HashPrune, a novel online pruning algorithm that enables efficient billion-scale index construction on a single machine. - [Pyramid Product Quantization](https://vectordb.ever.works/ja/items/pyramid-product-quantization) — An advanced vector compression technique for approximate nearest neighbor search that improves upon traditional product quantization by using a hierarchical pyramid structure. Published in 2026, it achieves better compression ratios while maintaining search accuracy. - [Scalable Distributed Vector Search](https://vectordb.ever.works/ja/items/scalable-distributed-vector-search) — A research paper on accuracy-preserving index construction for distributed vector search systems. Published in 2025, it addresses the challenge of maintaining search quality while distributing vector indexes across multiple nodes. - [UMAP](https://vectordb.ever.works/ja/items/umap-dimensionality-reduction) — Uniform Manifold Approximation and Projection - a dimensionality reduction technique used for visualizing high-dimensional vector embeddings and compressing vectors while preserving structure. Popular for embedding analysis and visualization. - [Distance Metrics for Vector Search](https://vectordb.ever.works/ja/items/distance-metrics-for-vector-search) — Overview of distance metrics including Euclidean, cosine similarity, dot product, and Manhattan distance, with guidance on when to use each for optimal retrieval performance. - [Vector Index Types Comparison](https://vectordb.ever.works/ja/items/vector-index-types-comparison) — Comprehensive comparison of vector indexing algorithms including Flat, IVF, HNSW, DiskANN, and Product Quantization, covering trade-offs in accuracy, speed, memory usage, and scalability. --- _Canonical page: https://vectordb.ever.works/ja/tags/algorithms_