Fast Label Embeddings via Randomized Linear Algebra
نویسندگان
چکیده
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency. In this work we utilize a correspondence between rank constrained estimation and low dimensional label embeddings that uncovers a fast label embedding algorithm which works in both the multiclass and multilabel settings. The result is a randomized algorithm whose running time is exponentially faster than naive algorithms. We demonstrate our techniques on two large-scale public datasets, from the Large Scale Hierarchical Text Challenge and the Open Directory Project, where we obtain state of the art results.
منابع مشابه
Fast Label Embeddings for Extremely Large Output Spaces
Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency. In this work we utilize a correspondence between rank constrained estimation and low dimensional label embeddings that uncovers a fast label embedding algorit...
متن کاملLarge-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings
We present a scalable Bayesian multi-label learning model based on learning lowdimensional label embeddings. Our model assumes that each label vector is generated as a weighted combination of a set of topics (each topic being a distribution over labels), where the combination weights (i.e., the embeddings) for each label vector are conditioned on the observed feature vector. This construction, ...
متن کاملTime for dithering: fast and quantized random embeddings via the restricted isometry property
Recently,manyworks have focused on the characterization of nonlinear dimensionality reductionmethods obtained by quantizing linear embeddings, e.g. to reach fast processing time, efficient data compression procedures, novel geometry-preserving embeddings or to estimate the information/bits stored in this reduced data representation. In this work, we prove that many linear maps known to respect ...
متن کاملThe Augmented Tridiagonal Algebra
Motivated by investigations of the tridiagonal pairs of linear transformations, we introduce the augmented tridiagonal algebra Tq. This is an infinite-dimensional associative C-algebra with 1. We classify the finite-dimensional irreducible representations of Tq. All such representations are explicitly constructed via embeddings of Tq into the Uq(sl2)-loop algebra. As an application, tridiagonal...
متن کاملFast Nearest Neighbor Preserving Embeddings
We show an analog to the Fast Johnson-Lindenstrauss Transform for Nearest Neighbor Preserving Embeddings in `2. These are sparse, randomized embeddings that preserve the (approximate) nearest neighbors. The dimensionality of the embedding space is bounded not by the size of the embedded set n, but by its doubling dimension λ. For most large real-world datasets this will mean a considerably lowe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2015