Related papers: LSI: A Learned Secondary Index Structure

The Differentiable Search Index (DSI) is a novel information retrieval (IR) framework that utilizes a differentiable function to generate a sorted list of document identifiers in response to a given query. However, due to the black-box…

Differentiable Search Indexing (DSI) is a recent paradigm for information retrieval which uses a transformer-based neural network architecture as the document index to simplify the retrieval process. A differentiable index has many…

Learned indexes use machine learning models to learn the mappings between keys and their corresponding positions in key-value indexes. These indexes use the mapping information as training data. Learned indexes require frequent retrainings…

Hyperspectral imaging (HSI) shows great promise for surgical applications, offering detailed insights into biological tissue differences beyond what the naked eye can perceive. Refined labelling efforts are underway to train vision systems…

Recent research on learned indexes has created a new perspective for indexes as models that map keys to their respective storage locations. These learned indexes are created to approximate the cumulative distribution function of the key…

In domains where sample sizes are limited, efficient learning algorithms are critical. Learning using privileged information (LuPI) offers increased sample efficiency by allowing prediction models access to auxiliary information at training…

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the…

Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes, its theoretical characterization remains elusive. To the…

We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences. Most often in the supervised learning to rank literature, ranking is approached either by analyzing pairs of…

Although many updatable learned indexes have been proposed in recent years, whether they can outperform traditional approaches on disk remains unknown. In this study, we revisit and implement four state-of-the-art updatable learned indexes…

Learned index structures aim to accelerate queries by training machine learning models to approximate the rank function associated with a database attribute. While effective in practice, their theoretical limitations are not fully…

A treap is a classic randomized binary search tree data structure that is easy to implement and supports O(\log n) expected time access. However, classic treaps do not take advantage of the input distribution or patterns in the input. Given…

In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel…

Statistical learning in high-dimensional spaces is challenging without a strong underlying data structure. Recent advances with foundational models suggest that text and image data contain such hidden structures, which help mitigate the…

Recent research has shown that learned models can outperform state-of-the-art index structures in size and lookup performance. While this is a very promising result, existing learned structures are often cumbersome to implement and are slow…

Accurately estimating the informativeness of individual samples in a dataset is an important objective in deep learning, as it can guide sample selection, which can improve model efficiency and accuracy by removing redundant or potentially…

Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the…

We show how perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features. Our perceptual embeddings are solutions to a weighted least squares (WLS) problem, defined at…

Binary search trees (BST) are a popular type of data structure when dealing with ordered data. Indeed, they enable one to access and modify data efficiently, with their height corresponding to the worst retrieval time. From a probabilistic…

Existing learned indexes (e.g., RMI, ALEX, PGM) optimize the internal regressor of each node, not the overall structure such as index height, the size of each layer, etc. In this paper, we share our recent findings that we can achieve…