paper-with-me

Papers

Linear Regression using Heterogeneous Data Batches

2023-09-05 · Ayush Jain, Rajat Sen, Weihao Kong, Abhimanyu Das, Alon Orlitsky

In many learning applications, data are collected from multiple sources, each providing a \emph{batch} of samples that by itself is insufficient to learn its input-output relationship. A common approach assumes that the sources fall in one of several unknown subgroups, each with an unknown input distribution and input-output relationship. We consider one of this setup's most fundamental and important manifestations where the output is a noisy linear combination of the inputs, and there are $k$ subgroups, each with its own regression vector. Prior work~\cite{kong2020meta} showed that with abundant small-batches, the regression vectors can be learned with only few, $\tilde\Omega( k^{3/2})$, batches of medium-size with $\tilde\Omega(\sqrt k)$ samples each. However, the paper requires that the input distribution for all $k$ subgroups be isotropic Gaussian, and states that removing this assumption is an ``interesting and challenging problem". We propose a novel gradient-based algorithm that improves on the existing results in several ways. It extends the applicability of the algorithm by: (1) allowing the subgroups' underlying input distributions to be different, unknown, and heavy-tailed; (2) recovering all subgroups followed by a significant proportion of batches even for infinite $k$; (3) removing the separation requirement between the regression vectors; (4) reducing the number of batches and allowing smaller batch sizes.

📄 PDF Abstract BibTeX arXiv:2309.01973

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Efficient List-Decodable Regression using Batches

2022-11-23 · Abhimanyu Das, Ayush Jain, Weihao Kong, Rajat Sen

We begin the study of list-decodable linear regression using batches. In this setting only an $\alpha \in (0,1]$ fraction of the batches are genuine. Each genuine batch contains $\ge n$ i.i.d. samples from a common unkno…

regression

Batch List-Decodable Linear Regression via Higher Moments

2025-03-12 · Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar, Sihan Liu 외

We study the task of list-decodable linear regression using batches. A batch is called clean if it consists of i.i.d. samples from an unknown linear regression distribution. For a parameter $\alpha \in (0, 1/2)$, an unkn…

regression

EM for Mixture of Linear Regression with Clustered Data

2023-08-22 · Amirhossein Reisizadeh, Khashayar Gatmiry, Asuman Ozdaglar

Modern data-driven and distributed learning frameworks deal with diverse massive data generated by clients spread across heterogeneous environments. Indeed, data heterogeneity is a major bottleneck in scaling up many dis…

Federated Learningregression

Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression

2023-06-14 · Shahar Stein Ioushua, Inbar Hasidim, Ofer Shayevitz, Meir Feder

Learning algorithms that divide the data into batches are prevalent in many machine-learning applications, typically offering useful trade-offs between computational efficiency and performance. In this paper, we examine …

Computational Efficiencyregression

Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers

2021-10-13 · Yujing Ma, Florin Rusu, Kesheng Wu, Alexander Sim

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and t…

Extreme Multi-Label ClassificationGPUMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+1