January 26, 2020

3246 words 16 mins read

Paper Group ANR 1455

Network Revenue Management with Limited Switches: Known and Unknown Demand Distributions. Autonomous Airline Revenue Management: A Deep Reinforcement Learning Approach to Seat Inventory Control and Overbooking. Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization. Understanding Roles and Entities: Datasets and Models for N …

Network Revenue Management with Limited Switches: Known and Unknown Demand Distributions


Title	Network Revenue Management with Limited Switches: Known and Unknown Demand Distributions
Authors	David Simchi-Levi, Yunzong Xu, Jinglong Zhao
Abstract	This work is motivated by a practical concern from our retail partner. While they respect the advantages of dynamic pricing, they must limit the number of price changes to be within some constant. We study the classical price-based network revenue management problem, where a retailer has finite initial inventory of multiple resources to sell over a finite time horizon. We consider both known and unknown distribution settings, and derive policies that have the best-possible asymptotic performance in both settings. Our results suggest an intrinsic difference between the expected revenue associated with how many switches are allowed, which further depends on the number of resources. Our results are also the first to show a separation between the regret bounds associated with different number of resources.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01067v3
PDF	https://arxiv.org/pdf/1911.01067v3.pdf
PWC	https://paperswithcode.com/paper/network-revenue-management-with-limited
Repo
Framework

Autonomous Airline Revenue Management: A Deep Reinforcement Learning Approach to Seat Inventory Control and Overbooking


Title	Autonomous Airline Revenue Management: A Deep Reinforcement Learning Approach to Seat Inventory Control and Overbooking
Authors	Syed Arbab Mohd Shihab, Caleb Logemann, Deepak-George Thomas, Peng Wei
Abstract	Revenue management can enable airline corporations to maximize the revenue generated from each scheduled flight departing in their transportation network by means of finding the optimal policies for differential pricing, seat inventory control and overbooking. As different demand segments in the market have different Willingness-To-Pay (WTP), airlines use differential pricing, booking restrictions, and service amenities to determine different fare classes or products targeted at each of these demand segments. Because seats are limited for each flight, airlines also need to allocate seats for each of these fare classes to prevent lower fare class passengers from displacing higher fare class ones and set overbooking limits in anticipation of cancellations and no-shows such that revenue is maximized. Previous work addresses these problems using optimization techniques or classical Reinforcement Learning methods. This paper focuses on the latter problem - the seat inventory control problem - casting it as a Markov Decision Process to be able to find the optimal policy. Multiple fare classes, concurrent continuous arrival of passengers of different fare classes, overbooking and random cancellations that are independent of class have been considered in the model. We have addressed this problem using Deep Q-Learning with the goal of maximizing the reward for each flight departure. The implementation of this technique allows us to employ large continuous state space but also presents the potential opportunity to test on real time airline data. To generate data and train the agent, a basic air-travel market simulator was developed. The performance of the agent in different simulated market scenarios was compared against theoretically optimal solutions and was found to be nearly close to the expected optimal revenue.
Tasks	Q-Learning
Published	2019-02-18
URL	https://arxiv.org/abs/1902.06824v2
PDF	https://arxiv.org/pdf/1902.06824v2.pdf
PWC	https://paperswithcode.com/paper/towards-the-next-generation-airline-revenue
Repo
Framework

Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization


Title	Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization
Authors	Qi Deng, Chenghao Lan
Abstract	Novel coordinate descent (CD) methods are proposed for minimizing nonconvex functions consisting of three terms: (i) a continuously differentiable term, (ii) a simple convex term, and (iii) a concave and continuous term. First, by extending randomized CD to nonsmooth nonconvex settings, we develop a coordinate subgradient method that randomly updates block-coordinate variables by using block composite subgradient mapping. This method converges asymptotically to critical points with proven sublinear convergence rate for certain optimality measures. Second, we develop a randomly permuted CD method with two alternating steps: linearizing the concave part and cycling through variables. We prove asymptotic convergence to critical points and sublinear complexity rate for objectives with both smooth and concave parts. Third, we extend accelerated coordinate descent (ACD) to nonsmooth and nonconvex optimization to develop a novel randomized proximal DC algorithm whereby we solve the subproblem inexactly by ACD. Convergence is guaranteed with at most a few number of ACD iterations for each DC subproblem, and convergence complexity is established for identification of some approximate critical points. Fourth, we further develop the third method to minimize certain ill-conditioned nonconvex functions: weakly convex functions with high Lipschitz constant to negative curvature ratios. We show that, under specific criteria, the ACD-based randomized method has superior complexity compared to conventional gradient methods. Finally, an empirical study on sparsity-inducing learning models demonstrates that CD methods are superior to gradient-based methods for certain large-scale problems.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.00918v1
PDF	https://arxiv.org/pdf/1909.00918v1.pdf
PWC	https://paperswithcode.com/paper/efficiency-of-coordinate-descent-methods-for
Repo
Framework

Understanding Roles and Entities: Datasets and Models for Natural Language Inference


Title	Understanding Roles and Entities: Datasets and Models for Natural Language Inference
Authors	Arindam Mitra, Ishan Shrivastava, Chitta Baral
Abstract	We present two new datasets and a novel attention mechanism for Natural Language Inference (NLI). Existing neural NLI models, even though when trained on existing large datasets, do not capture the notion of entity and role well and often end up making mistakes such as “Peter signed a deal” can be inferred from “John signed a deal”. The two datasets have been developed to mitigate such issues and make the systems better at understanding the notion of “entities” and “roles”. After training the existing architectures on the new dataset we observe that the existing architectures does not perform well on one of the new benchmark. We then propose a modification to the “word-to-word” attention function which has been uniformly reused across several popular NLI architectures. The resulting architectures perform as well as their unmodified counterparts on the existing benchmarks and perform significantly well on the new benchmark for “roles” and “entities”.
Tasks	Natural Language Inference
Published	2019-04-22
URL	http://arxiv.org/abs/1904.09720v1
PDF	http://arxiv.org/pdf/1904.09720v1.pdf
PWC	https://paperswithcode.com/paper/understanding-roles-and-entities-datasets-and
Repo
Framework

Bounds on Bayes Factors for Binomial A/B Testing


Title	Bounds on Bayes Factors for Binomial A/B Testing
Authors	Maciej Skorski
Abstract	Bayes factors, in many cases, have been proven to bridge the classic -value based significance testing and bayesian analysis of posterior odds. This paper discusses this phenomena within the binomial A/B testing setup (applicable for example to conversion testing). It is shown that the bayes factor is controlled by the \emph{Jensen-Shannon divergence} of success ratios in two tested groups, which can be further bounded by the Welch statistic. As a result, bayesian sample bounds almost match frequentionist’s sample bounds. The link between Jensen-Shannon divergence and Welch’s test as well as the derivation are an elegant application of tools from information geometry.
Tasks
Published	2019-02-28
URL	http://arxiv.org/abs/1903.00049v1
PDF	http://arxiv.org/pdf/1903.00049v1.pdf
PWC	https://paperswithcode.com/paper/bounds-on-bayes-factors-for-binomial-ab
Repo
Framework

MarlRank: Multi-agent Reinforced Learning to Rank


Title	MarlRank: Multi-agent Reinforced Learning to Rank
Authors	Shihao Zou, Zhonghua Li, Mohammad Akbari, Jun Wang, Peng Zhang
Abstract	When estimating the relevancy between a query and a document, ranking models largely neglect the mutual information among documents. A common wisdom is that if two documents are similar in terms of the same query, they are more likely to have similar relevance score. To mitigate this problem, in this paper, we propose a multi-agent reinforced ranking model, named MarlRank. In particular, by considering each document as an agent, we formulate the ranking process as a multi-agent Markov Decision Process (MDP), where the mutual interactions among documents are incorporated in the ranking process. To compute the ranking list, each document predicts its relevance to a query considering not only its own query-document features but also its similar documents features and actions. By defining reward as a function of NDCG, we can optimize our model directly on the ranking performance measure. Our experimental results on two LETOR benchmark datasets show that our model has significant performance gains over the state-of-art baselines. We also find that the NDCG shows an overall increasing trend along with the step of interactions, which demonstrates that the mutual information among documents helps improve the ranking performance.
Tasks	Document Ranking, Learning-To-Rank
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06859v1
PDF	https://arxiv.org/pdf/1909.06859v1.pdf
PWC	https://paperswithcode.com/paper/marlrank-multi-agent-reinforced-learning-to
Repo
Framework

Evaluating Voice Conversion-based Privacy Protection against Informed Attackers


Title	Evaluating Voice Conversion-based Privacy Protection against Informed Attackers
Authors	Brij Mohan Lal Srivastava, Nathalie Vauquier, Md Sahidullah, Aurélien Bellet, Marc Tommasi, Emmanuel Vincent
Abstract	Speech data conveys sensitive speaker attributes like identity or accent. With a small amount of found data, such attributes can be inferred and exploited for malicious purposes: voice cloning, spoofing, etc. Anonymization aims to make the data unlinkable, i.e., ensure that no utterance can be linked to its original speaker. In this paper, we investigate anonymization methods based on voice conversion. In contrast to prior work, we argue that various linkage attacks can be designed depending on the attackers’ knowledge about the anonymization scheme. We compare two frequency warping-based conversion methods and a deep learning based method in three attack scenarios. The utility of converted speech is measured via the word error rate achieved by automatic speech recognition, while privacy protection is assessed by the increase in equal error rate achieved by state-of-the-art i-vector or x-vector based speaker verification. Our results show that voice conversion schemes are unable to effectively protect against an attacker that has extensive knowledge of the type of conversion and how it has been applied, but may provide some protection against less knowledgeable attackers.
Tasks	Speaker Verification, Speech Recognition, Voice Conversion
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03934v2
PDF	https://arxiv.org/pdf/1911.03934v2.pdf
PWC	https://paperswithcode.com/paper/evaluating-voice-conversion-based-privacy
Repo
Framework

Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech


Title	Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech
Authors	Hieu-Thi Luong, Junichi Yamagishi
Abstract	Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we propose a methodology to bootstrap a VC system from a pretrained speaker-adaptive TTS model and unify the techniques as well as the interpretations of these two tasks. Moreover by offloading the heavy data demand to the training stage of the TTS model, our VC system can be built using a small amount of target speaker speech data. It also opens up the possibility of using speech in a foreign unseen language to build the system. Our subjective evaluations show that the proposed framework is able to not only achieve competitive performance in the standard intra-language scenario but also adapt and convert using speech utterances in an unseen language.
Tasks	Voice Conversion
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06532v1
PDF	https://arxiv.org/pdf/1909.06532v1.pdf
PWC	https://paperswithcode.com/paper/bootstrapping-non-parallel-voice-conversion
Repo
Framework

Learning Disentangled Representations via Independent Subspaces


Title	Learning Disentangled Representations via Independent Subspaces
Authors	Maren Awiszus, Hanno Ackermann, Bodo Rosenhahn
Abstract	Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.~directly between persons while all other parts of the face remain unchanged. The network allows to generate modified images which appear like realistic images. Our model learns disentangled representations by weak supervision. We propose a localized resnet autoencoder optimized using several loss functions including a loss based on the semantic segmentation, which we interpret as masks, and a loss which enforces disentanglement by decomposition of the latent space into statistically independent subspaces. We evaluate the proposed solution w.r.t. disentanglement and generated image quality. Convincing results are demonstrated using the CelebA dataset.
Tasks	Semantic Segmentation
Published	2019-08-26
URL	https://arxiv.org/abs/1908.08989v1
PDF	https://arxiv.org/pdf/1908.08989v1.pdf
PWC	https://paperswithcode.com/paper/learning-disentangled-representations-via
Repo
Framework

Towards Fast Displaced Vertex Finding


Title	Towards Fast Displaced Vertex Finding
Authors	Kim Albertsson, Federico Meloni
Abstract	Many Standard Model extensions predict metastable massive particles that can be detected by looking for displaced decay vertices in the inner detector volume. Current approaches to search for these events in high-energy particle collisions rely on the presence of additional energetic signatures to make an online selection during data-taking, as the reconstruction of displaced vertices is computationally intensive. Enabling trigger-level reconstruction of displaced vertices could significantly enhance the reach of such searches. This work is a first step approximating the location of the primary vertex in an idealised detector geometry using a 4-layer dense neural networks for regression of the vertex location yielding a precision of $O(1\ \mathrm{mm})$ [$O(20\ \mathrm{mm})$] RMS in a low [high] track multiplicity environment.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10508v1
PDF	https://arxiv.org/pdf/1910.10508v1.pdf
PWC	https://paperswithcode.com/paper/towards-fast-displaced-vertex-finding
Repo
Framework

Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video


Title	Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video
Authors	Yueming Jin, Keyun Cheng, Qi Dou, Pheng-Ann Heng
Abstract	Automatic instrument segmentation in video is an essentially fundamental yet challenging problem for robot-assisted minimally invasive surgery. In this paper, we propose a novel framework to leverage instrument motion information, by incorporating a derived temporal prior to an attention pyramid network for accurate segmentation. Our inferred prior can provide reliable indication of the instrument location and shape, which is propagated from the previous frame to the current frame according to inter-frame motion flow. This prior is injected to the middle of an encoder-decoder segmentation network as an initialization of a pyramid of attention modules, to explicitly guide segmentation output from coarse to fine. In this way, the temporal dynamics and the attention network can effectively complement and benefit each other. As additional usage, our temporal prior enables semi-supervised learning with periodically unlabeled video frames, simply by reverse execution. We extensively validate our method on the public 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset with three different tasks. Our method consistently exceeds the state-of-the-art results across all three tasks by a large margin. Our semi-supervised variant also demonstrates a promising potential for reducing annotation cost in the clinical practice.
Tasks
Published	2019-07-18
URL	https://arxiv.org/abs/1907.07899v1
PDF	https://arxiv.org/pdf/1907.07899v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-temporal-prior-from-motion-flow
Repo
Framework

Posterior-Guided Neural Architecture Search


Title	Posterior-Guided Neural Architecture Search
Authors	Yizhou Zhou, Xiaoyan Sun, Chong Luo, Zheng-Jun Zha, Wenjun Zeng
Abstract	The emergence of neural architecture search (NAS) has greatly advanced the research on network design. Recent proposals such as gradient-based methods or one-shot approaches significantly boost the efficiency of NAS. In this paper, we formulate the NAS problem from a Bayesian perspective. We propose explicitly estimating the joint posterior distribution over pairs of network architecture and weights. Accordingly, a hybrid network representation is presented which enables us to leverage the Variational Dropout so that the approximation of the posterior distribution becomes fully gradient-based and highly efficient. A posterior-guided sampling method is then presented to sample architecture candidates and directly make evaluations. As a Bayesian approach, our posterior-guided NAS (PGNAS) avoids tuning a number of hyper-parameters and enables a very effective architecture sampling in posterior probability space. Interestingly, it also leads to a deeper insight into the weight sharing used in the one-shot NAS and naturally alleviates the mismatch between the sampled architecture and weights caused by the weight sharing. We validate our PGNAS method on the fundamental image classification task. Results on Cifar-10, Cifar-100 and ImageNet show that PGNAS achieves a good trade-off between precision and speed of search among NAS methods. For example, it takes 11 GPU days to search a very competitive architecture with 1.98% and 14.28% test errors on Cifar10 and Cifar100, respectively.
Tasks	Image Classification, Neural Architecture Search
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09557v2
PDF	https://arxiv.org/pdf/1906.09557v2.pdf
PWC	https://paperswithcode.com/paper/one-shot-neural-architecture-search-through-a
Repo
Framework

Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity


Title	Feature Learning to Automatically Assess Radiographic Knee Osteoarthritis Severity
Authors	Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E O’ Connor
Abstract	This chapter presents the investigations and the results of feature learning using convolutional neural networks to automatically assess knee osteoarthritis (OA) severity and the associated clinical and diagnostic features of knee OA from X-ray images. Also, this chapter demonstrates that feature learning in a supervised manner is more effective than using conventional handcrafted features for automatic detection of knee joints and fine-grained knee OA image classification. In the general machine learning approach to automatically assess knee OA severity, the first step is to localize the region of interest that is to detect and extract the knee joint regions from the radiographs, and the next step is to classify the localized knee joints based on a radiographic classification scheme such as Kellgren and Lawrence grades. First, the existing approaches for detecting (or localizing) the knee joint regions based on handcrafted features are reviewed and outlined. Next, three new approaches are introduced: 1) to automatically detect the knee joint region using a fully convolutional network, 2) to automatically assess the radiographic knee OA using CNNs trained from scratch for classification and regression of knee joint images to predict KL grades in ordinal and continuous scales, and 3) to quantify the knee OA severity optimizing a weighted ratio of two loss functions: categorical cross entropy and mean-squared error using multi-objective convolutional learning and ordinal regression. Two public datasets: the OAI and the MOST are used to evaluate the approaches with promising results that outperform existing approaches. In summary, this work primarily contributes to the field of automated methods for localization (automatic detection) and quantification (image classification) of radiographic knee OA.
Tasks	Image Classification
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08840v1
PDF	https://arxiv.org/pdf/1908.08840v1.pdf
PWC	https://paperswithcode.com/paper/feature-learning-to-automatically-assess
Repo
Framework

Fixed-Size Ordinally Forgetting Encoding Based Word Sense Disambiguation


Title	Fixed-Size Ordinally Forgetting Encoding Based Word Sense Disambiguation
Authors	Xi Zhu, Mingbin Xu, Hui Jiang
Abstract	In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN), while keeping the positional information between words. In our method, a FOFE-based FFNN is used to train a pseudo language model over unlabelled corpus, then the pre-trained language model is capable of abstracting the surrounding context of polyseme instances in labelled corpus into context embeddings. Next, we take advantage of these context embeddings towards WSD classification. We conducted experiments on several WSD data sets, which demonstrates that our proposed method can achieve comparable performance to that of the state-of-the-art approach at the expense of much lower computational cost.
Tasks	Language Modelling, Word Sense Disambiguation
Published	2019-02-23
URL	http://arxiv.org/abs/1902.10246v1
PDF	http://arxiv.org/pdf/1902.10246v1.pdf
PWC	https://paperswithcode.com/paper/fixed-size-ordinally-forgetting-encoding
Repo
Framework

Regression via Kirszbraun Extension


Title	Regression via Kirszbraun Extension
Authors	Armin Biess, Aryeh Kontorovich, Yury Makarychev, Hanan Zaichyk
Abstract	We present a framework for performing regression between two Hilbert spaces. We accomplish this via Kirszbraun’s extension theorem – apparently the first application of this technique to supervised learning – and analyze its statistical and computational aspects. We begin by formulating the correspondence problem in terms of quadratically constrained quadratic program (QCQP) regression. Then we describe a procedure for smoothing the training data, which amounts to regularizing hypothesis complexity via its Lipschitz constant. The Lipschitz constant is tuned via a Structural Risk Minimization (SRM) procedure, based on the covering-number risk bounds we derive. We apply our technique to learn a transformation between two robotic manipulators with different embodiments, and report promising results.
Tasks	Imitation Learning
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11930v2
PDF	https://arxiv.org/pdf/1905.11930v2.pdf
PWC	https://paperswithcode.com/paper/regression-via-kirszbraun-extension-with
Repo
Framework