recent years. However, existing approaches do not adequately address two key
challenges: (a) the ability to tackle problems with a large number (say
millions) of labels, and (b) the ability to handle data with missing labels. In
this paper, we directly address both these problems by studying the multi-label
problem in a generic empirical risk minimization (ERM) framework. Our
framework, despite being simple, is surprisingly able to encompass several
recent label-compression based methods which can be derived as special cases of
our method. To optimize the ERM problem, we develop techniques that exploit the
structure of specific loss functions - such as the squared loss function - to
offer efficient algorithms. We further show that our learning framework admits
formal excess risk bounds even in the presence of missing labels. Our risk
bounds are tight and demonstrate better generalization performance for low-rank
promoting trace-norm regularization when compared to (rank insensitive)
Frobenius norm regularization. Finally, we present extensive empirical results
on a variety of benchmark datasets and show that our methods perform
significantly better than existing label compression based methods and can
scale up to very large datasets such as the Wikipedia dataset. ER - TY - CONF AU - Mirowski, Piotr AU - Ranzato, Marc'Aurelio AU - LeCun, Yann A2 - of the NIPS 2010 Workshop on Deep Learning, Proceedings T1 - Dynamic Auto-Encoders for Semantic Indexing T2 - PB - CY - PY - 2010/ M2 - VL - IS - SP - EP - UR - http://yann.lecun.com/exdb/publis/pdf/mirowski-nipsdl-10.pdf M3 - KW - deep KW - kallimachos KW - lda KW - learning KW - model KW - toread L1 - SN - N1 - Neuer Tab N1 - AB - ER -