English
Related papers

Related papers: Learning Polynomial Transformations

200 papers

Tensor rank and low-rank tensor decompositions have many applications in learning and complexity theory. Most known algorithms use unfoldings of tensors and can only handle rank up to $n^{\lfloor p/2 \rfloor}$ for a $p$-th order tensor in…

Data Structures and Algorithms · Computer Science 2015-04-23 Rong Ge , Tengyu Ma

Distribution learning focuses on learning the probability density function from a set of data samples. In contrast, clustering aims to group similar objects together in an unsupervised manner. Usually, these two tasks are considered…

Machine Learning · Computer Science 2023-08-31 Guanfang Dong , Chenqiu Zhao , Anup Basu

The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are…

Machine Learning · Statistics 2015-03-13 Philipp Hennig

Tensor rank learning for canonical polyadic decomposition (CPD) has long been deemed as an essential yet challenging problem. In particular, since the tensor rank controls the complexity of the CPD model, its inaccurate learning would cause…

Machine Learning · Computer Science 2022-03-30 Lei Cheng , Zhongtao Chen , Qingjiang Shi , Yik-Chung Wu , Sergios Theodoridis

We present a fairly general framework for reducing $(\varepsilon, \delta)$ differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and…

Machine Learning · Statistics 2022-06-23 Hassan Ashtiani , Christopher Liaw

The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks. Despite various tricks and techniques that have been employed to alleviate the problem in practice,…

Machine Learning · Computer Science 2021-12-06 Yao Lu , Stephen Gould , Thalaiyasingam Ajanthan

Gaussian processes (GPs) provide flexible distributions over functions, with inductive biases controlled by a kernel. However, in many applications Gaussian processes can struggle with even moderate input dimensionality. Learning a low…

Machine Learning · Computer Science 2020-01-01 Ian A. Delbridge , David S. Bindel , Andrew Gordon Wilson

We prove a structural result for degree-$d$ polynomials. In particular, we show that any degree-$d$ polynomial, $p$ can be approximated by another polynomial, $p_0$, which can be decomposed as some function of polynomials $q_1,...,q_m$ with…

Probability · Mathematics 2012-08-17 Daniel M. Kane

Factorization machines and polynomial networks are supervised polynomial models based on an efficient low-rank decomposition. We extend these models to the multi-output setting, i.e., for learning vector-valued functions, with application…

Machine Learning · Statistics 2017-11-07 Mathieu Blondel , Vlad Niculae , Takuma Otsuka , Naonori Ueda

Even in low dimensions, sampling from multi-modal distributions is challenging. We provide the first sampling algorithm for a broad class of distributions -- including all Gaussian mixtures -- with a query complexity that is polynomial in…

Computation · Statistics 2025-10-24 Adrien Vacher , Omar Chehab , Anna Korba

Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions…

Machine Learning · Computer Science 2017-09-26 Boris Flach , Alexander Shekhovtsov , Ondrej Fikar

We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP). Our main result is that $\text{poly}(k,d,1/\alpha,1/\varepsilon,\log(1/\delta))$ samples are sufficient to estimate a mixture of $k$…

Machine Learning · Statistics 2024-04-24 Mohammad Afzali , Hassan Ashtiani , Christopher Liaw

Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data. However, the standard assumption is that we have sufficient data to estimate these moments to high accuracy. In this…

Machine Learning · Statistics 2019-03-13 Omer Gottesman , Weiwei Pan , Finale Doshi-Velez

This paper studies the problem of learning the large-scale Gaussian graphical models that are multivariate totally positive of order two ($\text{MTP}_2$). By introducing the concept of bridge, which commonly exists in large-scale sparse…

Machine Learning · Computer Science 2023-10-02 Xiwen Wang , Jiaxi Ying , Daniel P. Palomar

To infer a multilayer representation of high-dimensional count vectors, we propose the Poisson gamma belief network (PGBN) that factorizes each of its layers into the product of a connection weight matrix and the nonnegative real hidden…

Machine Learning · Statistics 2015-12-31 Mingyuan Zhou , Yulai Cong , Bo Chen

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

The Forster transform is a method of regularizing a dataset by placing it in {\em radial isotropic position} while maintaining some of its essential properties. Forster transforms have played a key role in a diverse range of settings…

Data Structures and Algorithms · Computer Science 2022-12-07 Ilias Diakonikolas , Christos Tzamos , Daniel M. Kane

The successes of modern deep machine learning methods are founded on their ability to transform inputs across multiple layers to build good high-level representations. It is therefore critical to understand this process of representation…

Machine Learning · Statistics 2023-05-26 Adam X. Yang , Maxime Robeyns , Edward Milsom , Ben Anson , Nandi Schoots , Laurence Aitchison

We study efficient algorithms for linear regression and covariance estimation in the absence of Gaussian assumptions on the underlying distributions of samples, making assumptions instead about only finitely-many moments. We focus on how…

We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives…

Data Structures and Algorithms · Computer Science 2025-02-25 Gautam Chandrasekaran , Adam R. Klivans , Lin Lin Lee , Konstantinos Stavropoulos
‹ Prev 1 4 5 6 7 8 10 Next ›