paper-with-me

홈 › Papers

Self-Similar Epochs: Value in Arrangement

2018-03-14 · ICLR 2019 5 · Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that sub-epochs comprise of independent random samples of the training data that may not preserve informative structure present in the full data. We hypothesize that the training can be more effective with {\em self-similar} arrangements that potentially allow each epoch to provide benefits of multiple ones. We study this for "matrix factorization" -- the common task of learning metric embeddings of entities such as queries, videos, or words from example pairwise associations. We construct arrangements that preserve the weighted Jaccard similarities of rows and columns and experimentally observe training acceleration of 3\%-37\% on synthetic and recommendation datasets. Principled arrangements of training examples emerge as a novel and potentially powerful enhancement to SGD that merits further exploration.

📄 PDF Abstract BibTeX arXiv:1803.05389

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Eigenvalues of Autoencoders in Training and at Initialization

2022-01-27 · Benjamin Dees, Susama Agarwala, Corey Lowman

In this paper, we investigate the evolution of autoencoders near their initialization. In particular, we study the distribution of the eigenvalues of the Jacobian matrices of autoencoders early in the training process, t…

Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches

2022-07-17 · Yuanzheng Ci, Chen Lin, Lei Bai, Wanli Ouyang

Contrastive-based self-supervised learning methods achieved great success in recent years. However, self-supervision requires extremely long training epochs (e.g., 800 epochs for MoCo v3) to achieve promising results, wh…

Contrastive LearningLinear evaluationSelf-Supervised Learning

LSH Microbatches for Stochastic Gradients: Value in Rearrangement

2019-05-01 · ICLR 2019 5 · Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias

Metric embeddings are immensely useful representations of associations between entities (images, users, search queries, words, and more). Embeddings are learned by optimizing a loss objective of the general form…

Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?

2020-03-12 · Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat

The landmark achievements of AlphaGo Zero have created great research interest into self-play in reinforcement learning. In self-play, Monte Carlo Tree Search is used to train a deep neural network, that is then used in …

Reinforcement Learning

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

2023-05-22 · Emirhan Kurtulus, Zichao Li, Yann Dauphin, Ekin Dogus Cubuk

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and superv…

Data Augmentation