Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms

Mixture-of-Experts (MoE) is a widely popular model for ensemble learning and is a basic building block of highly successful modern neural networks as well as a component in Gated Recurrent Units (GRU) and Attention networks. However, present algorithms for learning MoE including the EM algorithm, and gradient descent are known to get stuck in local optima. From a theoretical viewpoint, finding an efficient and provably consistent algorithm to learn the parameters remains a long standing open problem for more than two decades. In this paper, we introduce the first algorithm that learns the true parameters of a MoE model for a wide class of non-linearities with global consistency guarantees. While existing algorithms jointly or iteratively estimate the expert parameters and the gating paramters in the MoE, we propose a novel algorithm that breaks the deadlock and can directly estimate the expert parameters by sensing its echo in a carefully designed cross-moment tensor between the inputs and the output. Once the experts are known, the recovery of gating parameters still requires an EM algorithm; however, we show that the EM algorithm for this simplified problem, unlike the joint EM algorithm, converges to the true parameters. We empirically validate our algorithm on both the synthetic and real data sets in a variety of settings, and show superior performance to standard baselines.

Deepcode: Feedback Codes via Deep Learning

The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly beats state-of-the-art codes designed over several decades of research. The communication channel under consideration is the Gaussian noise channel with feedback, whose study was initiated by Shannon; feedback is known theoretically to improve reliability of communication, but no practical codes that do so have ever been successfully constructed. We break this logjam by integrating information theoretic insights harmoniously with recurrent-neural-network based encoders and decoders to create novel codes that outperform known codes by 3 orders of magnitude in reliability. We also demonstrate several desirable properties of the codes: (a) generalization to larger block lengths, (b) composability with known codes, (c) adaptation to practical constraints. This result also has broader ramifications for coding theory: even when the channel has a clear mathematical model, deep learning methodologies, when combined with channel-specific information-theoretic insights, can potentially beat state-of-the-art codes constructed over decades of mathematical research.

Embedding Syntax and Semantics of Prepositions via Tensor Decomposition

Prepositions are among the most frequent words in English and play complex roles in the syntax and semantics of sentences. Not surprisingly, they pose well-known difficulties in automatic processing of sentences (prepositional attachment ambiguities and idiosyncratic uses in phrases). Existing methods on preposition representation treat prepositions no different from content words (e.g., word2vec and GloVe). In addition, recent studies aiming at solving prepositional attachment and preposition selection problems depend heavily on external linguistic resources and use dataset-specific word representations. In this paper we use word-triple counts (one of the triples being a preposition) to capture a preposition's interaction with its attachment and complement. We then derive preposition embeddings via tensor decomposition on a large unlabeled corpus. We reveal a new geometry involving Hadamard products and empirically demonstrate its utility in paraphrasing phrasal verbs. Furthermore, our preposition embeddings are used as simple features in two challenging downstream tasks: preposition selection and prepositional attachment disambiguation. We achieve results comparable to or better than the state-of-the-art on multiple standardized datasets.

Communication Algorithms via Deep Learning

Coding theory is a central discipline underpinning wireline and wireless modems that are the workhorses of the information age. Progress in coding theory is largely driven by individual human ingenuity with sporadic breakthroughs over the past century. In this paper we study whether it is possible to automate the discovery of decoding algorithms via deep learning. We study a family of sequential codes parameterized by recurrent neural network (RNN) architectures. We show that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel, which itself is achieved by breakthrough algorithms of our times (Viterbi and BCJR decoders, representing dynamic programing and forward-backward algorithms). We show strong generalizations, i.e., we train at a specific signal to noise ratio and block length but test at a wide range of these quantities, as well as robustness and adaptivity to deviations from the AWGN setting.

All-but-the-Top: Simple and Effective Postprocessing for Word Representations

Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a few top dominating directions from the word vectors -- that renders off-the-shelf representations {\em even stronger}. The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.

Discovering Potential Correlations via Hypercontractivity

Discovering a correlation from one variable to another variable is of fundamental scientific and practical interest. While existing correlation measures are suitable for discovering average correlation, they fail to discover hidden or potential correlations. To bridge this gap, (i) we postulate a set of natural axioms that we expect a measure of potential correlation to satisfy; (ii) we show that the rate of information bottleneck, i.e., the hypercontractivity coefficient, satisfies all the proposed axioms; (iii) we provide a novel estimator to estimate the hypercontractivity coefficient from samples; and (iv) we provide numerical experiments demonstrating that this proposed estimator discovers potential correlations among various indicators of WHO datasets, is robust in discovering gene interactions from gene expression time series data, and is statistically more powerful than the estimators for other correlation measures in binary hypothesis testing of canonical examples of potential correlations.

MORSE: Semantic-ally Drive-n MORpheme SEgment-er

We present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes. This framework is the first to consider vocabulary-wide syntactico-semantic information for this task. We also analyze the deficiencies of available benchmarking datasets and introduce our own dataset that was created on the basis of compositionality. We validate our algorithm across datasets and present state-of-the-art results.

Representing Sentences as Low-Rank Subspaces

Sentences are important semantic units of natural language. A generic, distributional representation of sentences that can capture the latent semantics is beneficial to multiple downstream applications. We observe a simple geometry of sentences -- the word representations of a given sentence (on average 10.23 words in all SemEval datasets with a standard deviation 4.84) roughly lie in a low-rank subspace (roughly, rank 4). Motivated by this observation, we represent a sentence by the low-rank subspace spanned by its word vectors. Such an unsupervised representation is empirically validated via semantic textual similarity tasks on 19 different datasets, where it outperforms the sophisticated neural network models, including skip-thought vectors, by 15% on average.

Fixing the Infix: Unsupervised Discovery of Root-and-Pattern Morphology

We present an unsupervised and language-agnostic method for learning root-and-pattern morphology in Semitic languages. This form of morphology, abundant in Semitic languages, has not been handled in prior unsupervised approaches. We harness the syntactico-semantic information in distributed word representations to solve the long standing problem of root-and-pattern discovery in Semitic languages. Moreover, we construct an unsupervised root extractor based on the learned rules. We prove the validity of learned rules across Arabic, Hebrew, and Amharic, alongside showing that our root extractor compares favorably with a widely used, carefully engineered root extractor: ISRI.

Prepositions in Context

Prepositions are highly polysemous, and their variegated senses encode significant semantic information. In this paper we match each preposition's complement and attachment and their interplay crucially to the geometry of the word vectors to the left and right of the preposition. Extracting such features from the vast number of instances of each preposition and clustering them makes for an efficient preposition sense disambigution (PSD) algorithm, which is comparable to and better than state-of-the-art on two benchmark datasets. Our reliance on no external linguistic resource allows us to scale the PSD algorithm to a large WikiCorpus and learn sense-specific preposition representations -- which we show to encode semantic relations and paraphrasing of verb particle compounds, via simple vector operations.