English
Related papers

Related papers: Minimax Lower Bounds for Kronecker-Structured Dict…

200 papers

Kronecker regression is a highly-structured least squares problem $\min_{\mathbf{x}} \lVert \mathbf{K}\mathbf{x} - \mathbf{b} \rVert_{2}^2$, where the design matrix $\mathbf{K} = \mathbf{A}^{(1)} \otimes \cdots \otimes \mathbf{A}^{(N)}$ is…

Data Structures and Algorithms · Computer Science 2023-05-15 Matthew Fahrbach , Thomas Fu , Mehrdad Ghadiri

Dictionary learning aims at seeking a dictionary under which the training data can be sparsely represented. Methods in the literature typically formulate the dictionary learning problem as an optimization w.r.t. two variables, i.e.,…

Signal Processing · Electrical Eng. & Systems 2021-10-27 Cheng Cheng , Wei Dai

We present a convex formulation of dictionary learning for sparse signal decomposition. Convexity is obtained by replacing the usual explicit upper bound on the dictionary size by a convex rank-reducing term similar to the trace norm. In…

Machine Learning · Computer Science 2008-12-11 Francis Bach , Julien Mairal , Jean Ponce

Data complexity is an important concept in the natural sciences and related areas, but lacks a rigorous and computable definition. In this paper, we focus on a particular sense of complexity that is high if the data is structured in a way…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Louis Mahon

Sparse dictionary learning (SDL) has become a popular method for adaptively identifying parsimonious representations of a dataset, a fundamental problem in machine learning and signal processing. While most work on SDL assumes a training…

Statistics Theory · Mathematics 2018-02-27 Shashank Singh , Barnabás Póczos , Jian Ma

Recent work has demonstrated that using a carefully designed dictionary instead of a predefined one, can improve the sparsity in jointly representing a class of signals. This has motivated the derivation of learning methods for designing a…

Information Theory · Computer Science 2010-05-04 Kevin Rosenblum , Lihi Zelnik-Manor , Yonina C. Eldar

We analyze the decomposition of a data matrix, assumed to be a superposition of a low-rank component and a component which is sparse in a known dictionary, using a convex demixing method. We provide a unified analysis, encompassing both…

Machine Learning · Computer Science 2019-02-22 Sirisha Rambhatla , Xingguo Li , Jarvis Haupt

Separable, or Kronecker product, dictionaries provide natural decompositions for 2D signals, such as images. In this paper, we describe a highly parallelizable algorithm that learns such dictionaries which reaches sparse representations…

Machine Learning · Computer Science 2021-12-03 Cristian Rusu , Paul Irofti

The Kronecker coefficients are the decomposition multiplicities of the tensor product of two irreducible representations of the symmetric group. Unlike the Littlewood--Richardson coefficients, which are the analogues for the general linear…

Representation Theory · Mathematics 2023-06-09 Kyu-Hwan Lee

Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like…

Machine Learning · Computer Science 2017-12-05 Vaisakh Shaj , Puranjoy Bhattacharya

We consider minimax signal detection in the sequence model. Working with certain ellipsoids in the space of square-summable sequences of real numbers, with a ball of positive radius removed, we obtain upper and lower bounds for the minimax…

Statistics Theory · Mathematics 2017-12-27 Clement Marteau , Theofanis Sapatinas

We study the problem of learning a distribution from samples, when the underlying distribution is a mixture of product distributions over discrete domains. This problem is motivated by several practical applications such as crowd-sourcing,…

Machine Learning · Statistics 2014-05-20 Prateek Jain , Sewoong Oh

Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a…

Computation and Language · Computer Science 2016-04-05 Mo Yu , Mark Dredze , Raman Arora , Matthew Gormley

Sparse coding or sparse dictionary learning has been widely used to recover underlying structure in many kinds of natural data. Here, we provide conditions guaranteeing when this recovery is universal; that is, when sparse codes and…

Neurons and Cognition · Quantitative Biology 2016-11-18 Christopher J. Hillar , Friedrich T. Sommer

Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding…

Computation and Language · Computer Science 2016-10-14 Yunchuan Chen , Lili Mou , Yan Xu , Ge Li , Zhi Jin

This paper considers the subject of information losses arising from the finite datasets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated…

Machine Learning · Computer Science 2020-01-09 Brandon Foggo , Nanpeng Yu , Jie Shi , Yuanqi Gao

The field of compressed sensing has shown that a sparse but otherwise arbitrary vector can be recovered exactly from a small number of randomly constructed linear projections (or samples). The question addressed in this paper is whether an…

Information Theory · Computer Science 2010-01-26 Galen Reeves , Michael Gastpar

Structured prediction can be considered as a generalization of many standard supervised learning tasks, and is usually thought as a simultaneous prediction of multiple labels. One standard approach is to maximize a score function on the…

Machine Learning · Computer Science 2021-02-19 Kevin Bello , Asish Ghoshal , Jean Honorio

Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn 'a good vector' for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can…

Computation and Language · Computer Science 2017-07-21 Aurelie Herbelot , Marco Baroni

This paper proposes a simple approach to derive efficient error bounds for learning multiple components with sparsity-inducing regularization. We show that for such regularization schemes, known decompositions of the Rademacher complexity…

Machine Learning · Statistics 2020-01-24 Fabien Lauer
‹ Prev 1 3 4 5 6 7 10 Next ›