arXiv subjects

Matthijs Douze

Publications and source records attributed to Matthijs Douze.

At least 19 recordsLinked to original sources

arXiv2026

Cluster with Auctions for Vector Search

Large-scale approximate nearest neighbor search commonly relies on partitions for indexing: database vectors are partitioned into clusters, and for each query a probing function selects the clusters to be scanned. The query probing function and the database partition are rarely treated as separate entities: most techniques assign queries with the same assignment function as the database vectors, which is suboptimal especially when database and query distributions differ. This paper introduces CwA (Cluster with Auctions), which addresses this limitation by jointly learning a balanced database partition and a neural probing function. CwA optimizes search performance directly for the query distribution. It minimizes its objective by alternating two steps: (i) gradient descent on the neural network of the probing function, and (ii) a large-scale combinatorial optimization of the cluster assignment for the database vectors. We solve the latter with a parallelizable auction algorithm that balances the partition by design. To further scale CwA, we extend the method to a Cartesian product of clusters that increases the partition's granularity. When database and query distributions differ, CwA achieves up to 4.7$\times$ throughput over the state-of-the-art at equal recall. In the in-distribution (ID) setting, even a simple linear probing function trained with CwA outperforms competing deep neural methods.

cs.IR↗

arXiv2026

Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity

Linear attention models allow a fixed state size and a fixed amount of compute per token. However, due to their limited state size, linear attention models fall behind in long-context recall compared to softmax-attention-based transformer architectures. Increasing the state size of linear attention improves recall performance but at the cost of higher FLOPs. In this work, we introduce Sparse Delta Memory (SDM), an architecture that scales the hidden state of gated linear RNNs to orders of magnitude higher capacity using a sparse addressing scheme. SDM extends the Gated DeltaNet architecture by replacing the dense key-value outer product with sparse reads and writes to a large explicit memory. We show that, under an isoFLOP constraint and with an identical number of parameters, a higher state memory capacity significantly improves performance on in-context learning and long-context retrieval tasks. Moreover, by learning the initial state of the SDM memory and therefore using it as a parametric memory, we show that the model further improves on a wide range of common-knowledge and reasoning tasks.

cs.LG↗

arXiv2026

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth. To address this limitation, we introduce Self-Pruned Key-Value Attention (SP-KV), a mechanism designed to predict future KV utility in order to reduce the size of the long-term KV cache. This strategy operates at a fine granularity: a lightweight utility predictor scores each key-value pair, and while recent KVs are always available via a local window, older pairs are written in the cache and used in global attention only if their predicted utility surpasses a given threshold. The LLM and the utility predictor are trained jointly end-to-end exclusively through next-token prediction loss, and are adapted from pretrained LLM checkpoints. Rather than enforcing a fixed compression ratio, SP-KV performs dynamic sparsification: the mechanism adapts to the input and typically reduces the KV cache size by a factor of $3$ to $10\times$, longer sequences often being more compressible. This leads to vast improvements in memory usage and decoding speed, with little to no degradation of validation loss nor performance on a broad set of downstream tasks. Beyond serving as an effective KV-cache reduction mechanism, our method reveals structured layer- and head-specific sparsity patterns that we can use to guide the design of hybrid local-global attention architectures.

cs.LG↗

arXiv2025

Short window attention enables long-term memorization

Recent works show that hybrid architectures combining local sliding window attention layers and global attention layers outperform either of these architectures taken separately. However, the impact of the window length and the interplay between local layers and global layers remain under-studied. In this work, we first analyze the interaction between short and long term memory by considering SWAX: a hybrid architecture consisting of sliding-window attention and xLSTM linear RNN layers. A counter-intuitive finding is that larger sliding windows hurts the long-context performance. In fact, short window attention encourages the model to better train the long-term memory of the xLSTM as it cannot rely on the local softmax attention mechanism for long context-retrieval. We also validate our findings on local-global architectures alternating short window and full attention layers: the short layers should be small in order not to hinder the usefulness of the long layers. However, employing too small sliding windows is detrimental even for short-context tasks, which could be solved with information from moderately larger sliding windows otherwise. Therefore, we train hybrid architectures by stochastically changing the sliding window size, forcing the model to leverage both the short term window and the long-term memory. Training with stochastic window sizes significantly outperforms regular window attention both on short and long-context problems.

cs.LG↗

arXiv2025

Stochastic activations

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw. This strategy circumvents the optimization problem associated with RELU, namely, the constant shape for negative inputs that prevents the gradient flow. We leverage this strategy in two ways: (1) We use stochastic activations during pre-training and fine-tune the model with RELU, which is used at inference time to provide sparse latent vectors. This reduces the inference FLOPs and translates into a significant speedup on CPU and GPU. This leads to better results than training from scratch with the RELU activation function. (2) We evaluate stochastic activations for sequence generation. This strategy performs reasonably well: it has higher diversity and has only slightly inferior performance to the best deterministic non-linearity, SILU, combined with temperature sampling. This provides an alternative way to increase the diversity of generated text.

cs.LG↗

arXiv2025

Machine learning and high dimensional vector search

Machine learning and vector search are two research topics that developed in parallel in nearby communities. However, unlike many other fields related to big data, machine learning has not significantly impacted vector search. In this opinion paper we attempt to explain this oddity. Along the way, we wander over the numerous bridges between the two fields.

cs.LG↗

arXiv2025

Inference-time sparse attention with asymmetric indexing

Self-attention in transformer models is an incremental associative memory that maps key vectors to value vectors. One way to speed up self-attention is to employ GPU-compatible vector search algorithms based on standard partitioning methods such as k-means. However, such partitioning methods yield poor results in this context because (1) the keys and queries follow different distributions, and (2) the RoPE positional encoding hinders the bucket assignment. This paper introduces Saap (Self-Attention with Asymmetric Partitions), which overcomes these problems. It is an asymmetrical indexing technique that employs distinct partitions for keys and queries, thereby approximating self-attention with a data-adaptive sparsity pattern. It works on pretrained language models and only requires to train (offline) a small query classifier. On a long context Llama 3.1-8b model, with sequences ranging from 100k to 500k tokens, Saap typically reduces by a factor of 20 the fraction of memory that needs to be looked-up, which translates to a time saving of 60\% when compared to FlashAttention-v2.

cs.CL↗

arXiv2025

Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search

Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can be served from a machine. Lossy vector compression, i.e., embedding quantization, has been applied extensively to reduce the size of indexes. However, for inverted file and graph-based indices, auxiliary data such as vector ids and links (edges) can represent most of the storage cost. We introduce and evaluate lossless compression schemes for these cases. These approaches are based on asymmetric numeral systems or wavelet trees that exploit the fact that the ordering of ids is irrelevant within the data structures. In some settings, we are able to compress the vector ids by a factor 7, with no impact on accuracy or search runtime. On billion-scale datasets, this results in a reduction of 30% of the index size. Furthermore, we show that for some datasets, these methods can also compress the quantized vector codes losslessly, by exploiting sub-optimalities in the original quantization algorithm. The source code for our approach available at https://github.com/facebookresearch/vector_db_id_compression.

cs.LG↗

arXiv2025

Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks

Vector quantization is a fundamental technique for compression and large-scale nearest neighbor search. For high-accuracy operating points, multi-codebook quantization associates data vectors with one element from each of multiple codebooks. An example is residual quantization (RQ), which iteratively quantizes the residual error of previous steps. Dependencies between the different parts of the code are, however, ignored in RQ, which leads to suboptimal rate-distortion performance. QINCo recently addressed this inefficiency by using a neural network to determine the quantization codebook in RQ based on the vector reconstruction from previous steps. In this paper we introduce QINCo2 which extends and improves QINCo with (i) improved vector encoding using codeword pre-selection and beam-search, (ii) a fast approximate decoder leveraging codeword pairs to establish accurate short-lists for search, and (iii) an optimized training procedure and network architecture. We conduct experiments on four datasets to evaluate QINCo2 for vector compression and billion-scale nearest neighbor search. We obtain outstanding results in both settings, improving the state-of-the-art reconstruction MSE by 34% for 16-byte vector compression on BigANN, and search accuracy by 24% with 8-byte encodings on Deep1M.

cs.LG↗

arXiv2024

Watermark Anything with Localized Messages

Image watermarking methods are not tailored to handle small watermarked areas. This restricts applications in real-world scenarios where parts of the image may come from different sources or have been edited. We introduce a deep-learning model for localized image watermarking, dubbed the Watermark Anything Model (WAM). The WAM embedder imperceptibly modifies the input image, while the extractor segments the received image into watermarked and non-watermarked areas and recovers one or several hidden messages from the areas found to be watermarked. The models are jointly trained at low resolution and without perceptual constraints, then post-trained for imperceptibility and multiple watermarks. Experiments show that WAM is competitive with state-of-the art methods in terms of imperceptibility and robustness, especially against inpainting and splicing, even on high-resolution images. Moreover, it offers new capabilities: WAM can locate watermarked areas in spliced images and extract distinct 32-bit messages with less than 1 bit error from multiple small regions -- no larger than 10% of the image surface -- even for small 256x256 images. Training and inference code and model weights are available at https://github.com/facebookresearch/watermark-anything.

cs.CV↗

arXiv2024

MagicPIG: LSH Sampling for Efficient LLM Generation

Large language models (LLMs) with long context windows have gained significant attention. However, the KV cache, stored to avoid re-computation, becomes a bottleneck. Various dynamic sparse or TopK-based attention approximation methods have been proposed to leverage the common insight that attention is sparse. In this paper, we first show that TopK attention itself suffers from quality degradation in certain downstream tasks because attention is not always as sparse as expected. Rather than selecting the keys and values with the highest attention scores, sampling with theoretical guarantees can provide a better estimation for attention output. To make the sampling-based approximation practical in LLM generation, we propose MagicPIG, a heterogeneous system based on Locality Sensitive Hashing (LSH). MagicPIG significantly reduces the workload of attention computation while preserving high accuracy for diverse tasks. MagicPIG stores the LSH hash tables and runs the attention computation on the CPU, which allows it to serve longer contexts and larger batch sizes with high approximation accuracy. MagicPIG can improve decoding throughput by up to $5\times$ across various GPU hardware and achieve 54ms decoding latency on a single RTX 4090 for Llama-3.1-8B-Instruct model with a context of 96k tokens. The code is available at https://github.com/Infini-AI-Lab/MagicPIG.

cs.CL↗

arXiv2024

Results of the Big ANN: NeurIPS'23 competition

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect the growing complexity and diversity of workloads. Unlike prior challenges that emphasized scaling up classical ANN search ~\cite{DBLP:conf/nips/SimhadriWADBBCH21}, this competition addressed filtered search, out-of-distribution data, sparse and streaming variants of ANNS. Participants developed and submitted innovative solutions that were evaluated on new standard datasets with constrained computational resources. The results showcased significant improvements in search accuracy and efficiency over industry-standard baselines, with notable contributions from both academic and industrial teams. This paper summarizes the competition tracks, datasets, evaluation metrics, and the innovative approaches of the top-performing submissions, providing insights into the current advancements and future directions in the field of approximate nearest neighbor search.

cs.IR↗

arXiv2024

Vector search with small radiuses

In recent years, the dominant accuracy metric for vector search is the recall of a result list of fixed size (top-k retrieval), considering as ground truth the exact vector retrieval results. Although convenient to compute, this metric is distantly related to the end-to-end accuracy of a full system that integrates vector search. In this paper we focus on the common case where a hard decision needs to be taken depending on the vector retrieval results, for example, deciding whether a query image matches a database image or not. We solve this as a range search task, where all vectors within a certain radius from the query are returned. We show that the value of a range search result can be modeled rigorously based on the query-to-vector distance. This yields a metric for range search, RSM, that is both principled and easy to compute without running an end-to-end evaluation. We apply this metric to the case of image retrieval. We show that indexing methods that are adapted for top-k retrieval do not necessarily maximize the RSM. In particular, for inverted file based indexes, we show that visiting a limited set of clusters and encoding vectors compactly yields near optimal results.

cs.CV↗

arXiv2024

Watermarking Makes Language Models Radioactive

We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP protection either work only in settings where the suspected text is known or do not provide reliable statistical guarantees. We discover that, on the contrary, it is possible to reliably determine if a language model was trained on synthetic data if that data is output by a watermarked LLM. Our new methods, specialized for radioactivity, detects with a provable confidence weak residuals of the watermark signal in the fine-tuned LLM. We link the radioactivity contamination level to the following properties: the watermark robustness, its proportion in the training set, and the fine-tuning process. For instance, if the suspect model is open-weight, we demonstrate that training on watermarked instructions can be detected with high confidence ($p$-value $< 10^{-5}$) even when as little as $5\%$ of training text is watermarked.

cs.CR↗

arXiv2024

Residual Quantization with Implicit Neural Codebooks

Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such method, which iteratively quantizes the error of the previous step. While the error distribution is dependent on previously-selected codewords, this dependency is not accounted for in conventional RQ as it uses a fixed codebook per quantization step. In this paper, we propose QINCo, a neural RQ variant that constructs specialized codebooks per step that depend on the approximation of the vector from previous steps. Experiments show that QINCo outperforms state-of-the-art methods by a large margin on several datasets and code sizes. For example, QINCo achieves better nearest-neighbor search accuracy using 12-byte codes than the state-of-the-art UNQ using 16 bytes on the BigANN1M and Deep1M datasets.

cs.LG↗

arXiv2024

The Faiss library

Vector databases typically manage large collections of embedding vectors. Currently, AI applications are growing rapidly, and so is the number of embeddings that need to be stored and indexed. The Faiss library is dedicated to vector similarity search, a core functionality of vector databases. Faiss is a toolkit of indexing methods and related primitives used to search, cluster, compress and transform vectors. This paper describes the trade-off space of vector search and the design principles of Faiss in terms of structure, approach to optimization and interfacing. We benchmark key features of the library and discuss a few selected applications to highlight its broad applicability.

cs.LG↗

arXiv2023

Functional Invariants to Watermark Large Transformers

The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However, most existing approaches require to optimize the weights to imprint the watermark signal, which is not suitable at scale due to the computational cost. This paper explores watermarks with virtually no computational cost, applicable to a non-blind white-box setting (assuming access to both the original and watermarked networks). They generate functionally equivalent copies by leveraging the models' invariance, via operations like dimension permutations or scaling/unscaling. This enables to watermark models without any change in their outputs and remains stealthy. Experiments demonstrate the effectiveness of the approach and its robustness against various model transformations (fine-tuning, quantization, pruning), making it a practical solution to protect the integrity of large models.

cs.CR↗

arXiv2023

DeDrift: Robust Similarity Search under Content Drift

The statistical distribution of content uploaded and searched on media sharing sites changes over time due to seasonal, sociological and technical factors. We investigate the impact of this "content drift" for large-scale similarity search tools, based on nearest neighbor search in embedding space. Unless a costly index reconstruction is performed frequently, content drift degrades the search accuracy and efficiency. The degradation is especially severe since, in general, both the query and database distributions change. We introduce and analyze real-world image and video datasets for which temporal information is available over a long time period. Based on the learnings, we devise DeDrift, a method that updates embedding quantizers to continuously adapt large-scale indexing structures on-the-fly. DeDrift almost eliminates the accuracy degradation due to the query and database content drift while being up to 100x faster than a full index reconstruction.

cs.CV↗