Machine learning techniques have recently received significant attention as promising approaches to deal with the optical channel impairments, and in particular, the nonlinear effects. In this work, a machine learning-based classification technique, known as the Parzen window (PW) classifier, is applied to mitigate the nonlinear effects in the optical channel. The PW classifier is used as a detector with improved nonlinear decision boundaries more adapted to the nonlinear fiber channel. Performance improvement is observed when applying the PW in the context of dispersion managed and dispersion unmanaged systems.

We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function Tanh for Deep Learning. K-TanH consists of a sequence of parameterized bit/integer operations, such as, masking, shift and add/subtract (no floating point operation needed) where parameters are stored in a very small look-up table. The design of K-TanH is flexible enough to deal with multiple numerical formats, such as, FP32 and BFloat16. High quality approximations to other activation functions, e.g., Swish and GELU, can be derived from K-TanH. We provide RTL design for K-TanH to demonstrate its area/power/performance efficacy. It is more accurate than existing piecewise approximations for Tanh. For example, K-TanH achieves $\sim 5\times$ speed up and $> 6\times$ reduction in maximum approximation error over software implementation of Hard TanH. Experimental results for low-precision BFloat16 training of language translation model GNMT on WMT16 data sets with approximate Tanh and Sigmoid obtained via K-TanH achieve similar accuracy and convergence as training with exact Tanh and Sigmoid.

We propose a method for sim-to-real robot learning which exploits simulator state information in a way that scales to many objects. First, we train a pair of encoders on raw object pose targets to learn representations that accurately capture the state information of a multi-object environment. Second, we use these encoders in a reinforcement learning algorithm to train image-based policies capable of manipulating many objects. Our pair of encoders consists of one which consumes RGB images and is used in our policy network, and one which directly consumes a set of raw object poses and is used for reward calculation and value estimation. We evaluate our method on the task of pushing a collection of objects to desired tabletop regions. Compared to methods which rely only on images or use fixed-length state encodings, our method achieves higher success rates, performs well in the real world without fine tuning, and generalizes to different numbers and types of objects not seen during training.

September 18, 2019 Abstract The Wasserstein distance has risen in popularity in the statistics and machine learning communities as a useful metric for comparing probability distributions. We study the problem of uncertainty quantification for the Sliced Wasserstein distance--an easily computable approximation of the Wasserstein distance. Specifically, we construct confidence intervals for the Sliced Wasserstein distance which have finite-sample validity under no assumptions or mild moment assumptions, and are adaptive in length to the smoothness of the underlying distributions. We also bound the minimax risk of estimating the Sliced Wasserstein distance, and show that the length of our proposed confidence intervals is minimax optimal over appropriate distribution classes. To motivate the choice of these classes, we also study minimax rates of estimating a distribution under the Sliced Wasserstein distance. These theoretical findings are complemented with a simulation study. 1 Introduction The Wasserstein distance is a metric between probability distributions which has received a surge of interest in statistics and machine learning (Panaretos and Zemel, 2018; Kolouri et al., 2017). This distance is a special case of the optimal transport problem (Villani, 2003), and measures the work required to couple one distribution with another. Specifically, let P ( X) denote the set of Borel probability measures supported on a set X R d, for some integer d 1, and let P r(X) denote the set of probability measures with finite r -th moment, for some r 1.

Gaussian processes (GPs) are nonparametric priors over functions, and fitting a GP to the data implies computing the posterior distribution of the functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) [Damianou:2013] should allow us to compute the posterior distribution of compositions of multiple functions giving rise to the observations. However, exact Bayesian inference is usually intractable for DGPs, motivating the use of various approximations. We show that the simplifying assumptions for a common type of Variational inference approximation imply that all but one layer of a DGP collapse to a deterministic transformation. We argue that such an inference scheme is suboptimal, not taking advantage of the potential of the model to discover the compositional structure in the data, and propose possible modifications addressing this issue.

The trends of open science have enabled several open scholarly datasets which include millions of papers and authors. Managing, exploring, and utilizing such large and complicated datasets effectively are challenging. In recent years, the knowledge graph has emerged as a universal data format for representing knowledge about heterogeneous entities and their relationships. The knowledge graph can be modeled by knowledge graph embedding methods, which represent entities and relations as embedding vectors in semantic space, then model the interactions between these embedding vectors. However, the semantic structures in the knowledge graph embedding space are not well-studied, thus knowledge graph embedding methods are usually only used for knowledge graph completion but not data representation and analysis. In this paper, we propose to analyze these semantic structures based on the well-studied word embedding space and use them to support data exploration. We also define the semantic queries, which are algebraic operations between the embedding vectors in the knowledge graph embedding space, to solve queries such as similarity and analogy between the entities on the original datasets. We then design a general framework for data exploration by semantic queries and discuss the solution to some traditional scholarly data exploration tasks. We also propose some new interesting tasks that can be solved based on the uncanny semantic structures of the embedding space.

Event detection has long been the domain of physical sensors operating in a static dataset assumption. The prevalence of social media and web access has led to the emergence of social, or human sensors who report on events globally. This warrants development of event detectors that can take advantage of the truly dense and high spatial and temporal resolution data provided by more than 3 billion social users. The phenomenon of concept drift, which causes terms and signals associated with a topic to change over time, renders static machine learning ineffective. Towards this end, we present an application for physical event detection on social sensors that improves traditional physical event detection with concept drift adaptation. Our approach continuously updates its machine learning classifiers automatically, without the need for human intervention. It integrates data from heterogeneous sources and is designed to handle weak-signal events (landslides, wildfires) with around ten posts per event in addition to large-signal events (hurricanes, earthquakes) with hundreds of thousands of posts per event. We demonstrate a landslide detector on our application that detects almost 350% more land-slides compared to static approaches. Our application has high performance: using classifiers trained in 2014, achieving event detection accuracy of 0.988, compared to 0.762 for static approaches.

We consider efficiency in the implementation of deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph describing a neural network can be implemented as a directed graph describing a Boolean circuit. We make this observation precise, leading naturally to an understanding of practical neural networks as discrete functions, and show that so-called binarised neural networks are functionally complete. In general, our results suggest that it is valuable to consider Boolean circuits as neural networks, leading to the question of which circuit topologies are promising. We argue that continuity is central to generalisation in learning, explore the interaction between data coding, network topology, and node functionality for continuity, and pose some open questions for future research. As a first step to bridging the gap between continuous and Boolean views of neural network accelerators, we present some recent results from our work on LUTNet, a novel Field-Programmable Gate Array inference approach. Finally, we conclude with additional possible fruitful avenues for research bridging the continuous and discrete views of neural networks.

This study mainly investigates two decoding problems in neural keyphrase generation: sequence length bias and beam diversity. We introduce an extension of beam search inference based on word-level and n-gram level attention score to adjust and constrain Seq2Seq prediction at test time. Results show that our proposed solution can overcome the algorithm bias to shorter and nearly identical sequences, resulting in a significant improvement of the decoding performance on generating keyphrases that are present and absent in source text.

The widespread use of ML-based decision making in domains with high societal impact such as recidivism, job hiring and loan credit has raised a lot of concerns regarding potential discrimination. In particular, in certain cases it has been observed that ML algorithms can provide different decisions based on sensitive attributes such as gender or race and therefore can lead to discrimination. Although, several fairness-aware ML approaches have been proposed, their focus has been largely on preserving the overall classification accuracy while improving fairness in predictions for both protected and non-protected groups (defined based on the sensitive attribute(s)). The overall accuracy however is not a good indicator of performance in case of class imbalance, as it is biased towards the majority class. As we will see in our experiments, many of the fairness-related datasets suffer from class imbalance and therefore, tackling fairness requires also tackling the imbalance problem. To this end, we propose AdaFair, a fairness-aware classifier based on AdaBoost that further updates the weights of the instances in each boosting round taking into account a cumulative notion of fairness based upon all current ensemble members, while explicitly tackling class-imbalance by optimizing the number of ensemble members for balanced classification error. Our experiments show that our approach can achieve parity in true positive and true negative rates for both protected and non-protected groups, while it significantly outperforms existing fairness-aware methods up to 25% in terms of balanced error.