Neural Information Processing Systems http://nips.cc/

Transformers with multi-head self-attention have achieved remarkable success in sequence modeling and beyond. However, they suffer from high computational and memory complexities for computing the attention matrix at each head. Recently, it has been shown that those attention matrices lie on a low-dimensional manifold and, thus, are redundant. We propose the Transformer with a Finite Admixture of Shared Heads (FiSHformers), a novel class of efficient and flexible transformers that allow the sharing of attention matrices between attention heads. At the core of FiSHformer is a novel finite admixture model of shared heads (FiSH) that samples attention matrices from a set of global attention matrices. The number of global attention matrices is much smaller than the number of local attention matrices generated. FiSHformers directly learn these global attention matrices rather than the local ones as in other transformers, thus significantly improving the computational and memory efficiency of the model. We empirically verify the advantages of the FiSHformer over the baseline transformers in a wide range of practical applications including language modeling, machine translation, and image classification. On the WikiText-103, IWSLT'14 De-En and WMT'14 En-De, FiSHformers use much fewer floating-point operations per second (FLOPs), memory, and parameters compared to the baseline transformers.

We present a novel approach for LDA (Latent Dirichlet Allocation) topic reconstruction.

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. (2014) is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models (Mimno et al. 2011, Newman et al. 2010) and measures of model fitness (Mimno & Blei 2011) provide strong support that explicitly modeling word dependencies---as in APM---could be both semantically meaningful and essential for appropriately modeling real text data. Though APM shows significant promise for providing a better topic model, APM has a high computational complexity because $O(p^2)$ parameters must be estimated where $p$ is the number of words (Inouye et al. could only provide results for datasets with $p = 200$). In light of this, we develop a parallel alternating Newton-like algorithm for training the APM model that can handle $p = 10^4$ as an important step towards scaling to large datasets.

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model [1] and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. [1] is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models [2, 3, 4, 5] and measures of model fitness [6] provide strong support that explicitly modeling word dependencies--as in APM--could be both semantically meaningful and essential for appropriately modeling real text data.

Topic models, such as Latent Dirichlet Allocation (LDA), posit that documents are drawn from admixtures of distributions over words, known as topics. The inference problem of recovering topics from such a collection of documents drawn from admixtures, is NP-hard. Making a strong assumption called separability, [4] gave the first provable algorithm for inference. For the widely used LDA model, [6] gave a provable algorithm using clever tensor-methods.

Transformers with multi-head self-attention have achieved remarkable success in sequence modeling and beyond. However, they suffer from high computational and memory complexities for computing the attention matrix at each head. Recently, it has been shown that those attention matrices lie on a low-dimensional manifold and, thus, are redundant. We propose the Transformer with a Finite Admixture of Shared Heads (FiSHformers), a novel class of efficient and flexible transformers that allow the sharing of attention matrices between attention heads. At the core of FiSHformer is a novel finite admixture model of shared heads (FiSH) that samples attention matrices from a set of global attention matrices.

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. (2014) is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models (Mimno et al. 2011, Newman et al. 2010) and measures of model fitness (Mimno & Blei 2011) provide strong support that explicitly modeling word dependencies---as in APM---could be both semantically meaningful and essential for appropriately modeling real text data. Though APM shows significant promise for providing a better topic model, APM has a high computational complexity because O(p 2) parameters must be estimated where p is the number of words (Inouye et al. could only provide results for datasets with p 200). In light of this, we develop a parallel alternating Newton-like algorithm for training the APM model that can handle p 10 4 as an important step towards scaling to large datasets.

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model [1] and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. [1] is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models [2, 3, 4, 5] and measures of model fitness [6] provide strong support that explicitly modeling word dependencies--as in APM--could be both semantically meaningful and essential for appropriately modeling real text data.

We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model and propose a novel metric to directly evaluate this model. The APM topic model recently introduced by Inouye et al. (2014) is the first topic model that allows for word dependencies within each topic unlike in previous topic models like LDA that assume independence between words within a topic. Research in both the semantic coherence of a topic models (Mimno et al. 2011, Newman et al. 2010) and measures of model fitness (Mimno & Blei 2011) provide strong support that explicitly modeling word dependencies---as in APM---could be both semantically meaningful and essential for appropriately modeling real text data. Though APM shows significant promise for providing a better topic model, APM has a high computational complexity because $O(p 2)$ parameters must be estimated where $p$ is the number of words (Inouye et al. could only provide results for datasets with $p 200$). In light of this, we develop a parallel alternating Newton-like algorithm for training the APM model that can handle $p 10 4$ as an important step towards scaling to large datasets.