English
Related papers

Related papers: Simple Projection Variants Improve ColBERT Perform…

200 papers

In this paper, we consider the problem of learning high-dimensional tensor regression problems with low-rank structure. One of the core challenges associated with learning high-dimensional models is computation since the underlying…

Machine Learning · Statistics 2016-12-01 Han Chen , Garvesh Raskutti , Ming Yuan

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision…

Computer Vision and Pattern Recognition · Computer Science 2022-09-12 Zhengzhong Tu , Hossein Talebi , Han Zhang , Feng Yang , Peyman Milanfar , Alan Bovik , Yinxiao Li

With the rise of generative models, there is a growing interest in unifying all tasks within a generative framework. Anomaly detection methods also fall into this scope and utilize diffusion models to generate or reconstruct normal samples…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Xiaofan Li , Xin Tan , Zhuo Chen , Zhizhong Zhang , Ruixin Zhang , Rizen Guo , Guannan Jiang , Yulong Chen , Yanyun Qu , Lizhuang Ma , Yuan Xie

Network estimation from multi-variate point process or time series data is a problem of fundamental importance. Prior work has focused on parametric approaches that require a known parametric model, which makes estimation procedures less…

Machine Learning · Statistics 2021-06-30 Yue Gao , Garvesh Raskutti

Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions. However, this granularity imposes prohibitive storage and retrieval…

Information Retrieval · Computer Science 2026-05-29 Lixuan Guo , Yifei Wang , Tiansheng Wen , Aosong Feng , Stefanie Jegelka , Chenyu You

Deep neural networks have achieved great success both in computer vision and natural language processing tasks. However, mostly state-of-art methods highly rely on external training or computing to improve the performance. To alleviate the…

Machine Learning · Computer Science 2020-09-25 Ming Yan , Xueli Xiao , Joey Tianyi Zhou , Yi Pan

Given a reference model that includes all the available variables, projection predictive inference replaces its posterior with a constrained projection including only a subset of all variables. We extend projection predictive inference to…

Computation · Statistics 2021-09-13 Alejandro Catalina , Paul Bürkner , Aki Vehtari

The transformer model has gained widespread adoption in computer vision tasks in recent times. However, due to the quadratic time and memory complexity of self-attention, which is proportional to the number of input tokens, most existing…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Wei Tan , Yifeng Geng , Xuansong Xie

We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Convolutional predictors, such as the fully-convolutional…

Computer Vision and Pattern Recognition · Computer Science 2016-09-22 Aayush Bansal , Xinlei Chen , Bryan Russell , Abhinav Gupta , Deva Ramanan

We develop new theoretical results on matrix perturbation to shed light on the impact of architecture on the performance of a deep network. In particular, we explain analytically what deep learning practitioners have long observed…

Machine Learning · Computer Science 2022-12-06 Rudolf H. Riedi , Randall Balestriero , Richard G. Baraniuk

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Machine Learning · Computer Science 2024-11-05 Ian Pons , Bruno Yamamoto , Anna H. Reali Costa , Artur Jordao

Solving different types of optimization models (including parameters fitting) for support vector machines on large-scale training data is often an expensive computational task. This paper proposes a multilevel algorithmic framework that…

Machine Learning · Statistics 2014-10-14 Talayeh Razzaghi , Ilya Safro

This study explores the effectiveness of layer pruning for developing more efficient BERT models tailored to specific downstream tasks in low-resource languages. Our primary objective is to evaluate whether pruned BERT models can maintain…

Computation and Language · Computer Science 2025-01-03 Mayur Shirke , Amey Shembade , Madhushri Wagh , Pavan Thorat , Raviraj Joshi

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Machine Learning · Computer Science 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg

Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge. However, although the current advanced…

Computer Vision and Pattern Recognition · Computer Science 2022-10-21 Zeyue Xue , Jianming Liang , Guanglu Song , Zhuofan Zong , Liang Chen , Yu Liu , Ping Luo

Vision-Language Pre-Trained models, notably CLIP, that utilize contrastive learning have proven highly adept at extracting generalizable visual features. To inherit the well-learned knowledge of VLP models for downstream tasks, several…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Yi Zhang , Weicheng Lin , Liang-Jie Zhang

We reconsider randomized algorithms for the low-rank approximation of symmetric positive semi-definite (SPSD) matrices such as Laplacian and kernel matrices that arise in data analysis and machine learning applications. Our main results…

Machine Learning · Computer Science 2013-06-05 Alex Gittens , Michael W. Mahoney

When performing classification tasks, raw high dimensional features often contain redundant information, and lead to increased computational complexity and overfitting. In this paper, we assume the data samples lie on a single underlying…

Image and Video Processing · Electrical Eng. & Systems 2020-08-11 Bowen Jiang , Maohao Shen

Information projections are the key building block of variational inference algorithms and are used to approximate a target probabilistic model by projecting it onto a family of tractable distributions. In general, there is no guarantee on…

Machine Learning · Computer Science 2015-10-06 Lun-Kai Hsu , Tudor Achim , Stefano Ermon

Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce…

Information Retrieval · Computer Science 2022-07-12 Keshav Santhanam , Omar Khattab , Jon Saad-Falcon , Christopher Potts , Matei Zaharia