paper-with-me

홈 › Papers

Provable benefits of representation learning

2017-06-14 · Sanjeev Arora, Andrej Risteski

There is general consensus that learning representations is useful for a variety of reasons, e.g. efficient use of labeled data (semi-supervised learning), transfer learning and understanding hidden structure of data. Popular techniques for representation learning include clustering, manifold learning, kernel-learning, autoencoders, Boltzmann machines, etc. To study the relative merits of these techniques, it's essential to formalize the definition and goals of representation learning, so that they are all become instances of the same definition. This paper introduces such a formal framework that also formalizes the utility of learning the representation. It is related to previous Bayesian notions, but with some new twists. We show the usefulness of our framework by exhibiting simple and natural settings -- linear mixture models and loglinear models, where the power of representation learning can be formally shown. In these examples, representation learning can be performed provably and efficiently under plausible assumptions (despite being NP-hard), and furthermore: (i) it greatly reduces the need for labeled data (semi-supervised learning) and (ii) it allows solving classification tasks when simpler approaches like nearest neighbors require too much data (iii) it is more powerful than manifold learning methods.

📄 PDF Abstract BibTeX arXiv:1706.04601

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringRepresentation LearningTransfer Learning

Similar Papers 제목 키워드 기반

Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits

2019-01-21 · Xialiang Dou, Tengyuan Liang

Consider the problem: given the data pair $(\mathbf{x}, \mathbf{y})$ drawn from a population with $f_*(x) = \mathbf{E}[\mathbf{y} | \mathbf{x} = x]$, specify a neural network model and run gradient flow on the weights ov…

The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning

2023-02-27 · Hao Hu, Yiqin Yang, Qianchuan Zhao, Chongjie Zhang

Self-supervised methods have become crucial for advancing deep learning by leveraging data itself to reduce the need for expensive annotations. However, the question of how to conduct self-supervised offline reinforcemen…

Offline RLreinforcement-learningReinforcement Learning (RL)

Provable Representation Learning for Imitation Learning via Bi-level Optimization

2020-02-24 · ICML 2020 1 · Sanjeev Arora, Simon S. Du, Sham Kakade, Yuping Luo 외

A common strategy in modern learning systems is to learn a representation that is useful for many tasks, a.k.a. representation learning. We study this strategy in the imitation learning setting for Markov decision proces…

Imitation LearningRepresentation Learning

Kernel Two-Dimensional Ridge Regression for Subspace Clustering

2020-11-03 · Chong Peng, Qian Zhang, Zhao Kang, Chenglizhao Chen 외

Subspace clustering methods have been widely studied recently. When the inputs are 2-dimensional (2D) data, existing subspace clustering methods usually convert them into vectors, which severely damages inherent structur…

ClusteringregressionVocal Bursts Valence Prediction

Provable Pathways: Learning Multiple Tasks over Multiple Paths

2023-03-08 · Yingcong Li, Samet Oymak

Constructing useful representations across a large number of tasks is a key requirement for sample-efficient intelligent systems. A traditional idea in multitask learning (MTL) is building a shared representation across …

Generalization Bounds