Paper Group ANR 91
Optimal Bidding Strategy without Exploration in Real-time Bidding. Incremental Object Detection via Meta-Learning. Inference for linear forms of eigenvectors under minimal eigenvalue separation: Asymmetry and heteroscedasticity. Triad State Space Construction for Chaotic Signal Classification with Deep Learning. Autonomous Navigation in Unknown Env …
Optimal Bidding Strategy without Exploration in Real-time Bidding
| Title | Optimal Bidding Strategy without Exploration in Real-time Bidding |
| Authors | Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel, Viswanathan Swaminathan |
| Abstract | Maximizing utility with a budget constraint is the primary goal for advertisers in real-time bidding (RTB) systems. The policy maximizing the utility is referred to as the optimal bidding strategy. Earlier works on optimal bidding strategy apply model-based batch reinforcement learning methods which can not generalize to unknown budget and time constraint. Further, the advertiser observes a censored market price which makes direct evaluation infeasible on batch test datasets. Previous works ignore the losing auctions to alleviate the difficulty with censored states; thus significantly modifying the test distribution. We address the challenge of lacking a clear evaluation procedure as well as the error propagated through batch reinforcement learning methods in RTB systems. We exploit two conditional independence structures in the sequential bidding process that allow us to propose a novel practical framework using the maximum entropy principle to imitate the behavior of the true distribution observed in real-time traffic. Moreover, the framework allows us to train a model that can generalize to the unseen budget conditions than limit only to those observed in history. We compare our methods on two real-world RTB datasets with several baselines and demonstrate significantly improved performance under various budget settings. |
| Tasks | |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2004.00100v1 |
| https://arxiv.org/pdf/2004.00100v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-bidding-strategy-without-exploration |
| Repo | |
| Framework | |
Incremental Object Detection via Meta-Learning
| Title | Incremental Object Detection via Meta-Learning |
| Authors | K J Joseph, Jathushan Rajasegaran, Salman Khan, Fahad Shahbaz Khan, Vineeth Balasubramanian, Ling Shao |
| Abstract | In a real-world setting, object instances from new classes may be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to large-sized models for object detection. We evaluate our approach on a variety of incremental settings defined on PASCAL-VOC and MS COCO datasets, demonstrating significant improvements over state-of-the-art. |
| Tasks | Meta-Learning, Object Detection, Transfer Learning |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.08798v1 |
| https://arxiv.org/pdf/2003.08798v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-object-detection-via-meta |
| Repo | |
| Framework | |
Inference for linear forms of eigenvectors under minimal eigenvalue separation: Asymmetry and heteroscedasticity
| Title | Inference for linear forms of eigenvectors under minimal eigenvalue separation: Asymmetry and heteroscedasticity |
| Authors | Chen Cheng, Yuting Wei, Yuxin Chen |
| Abstract | A fundamental task that spans numerous applications is inference and uncertainty quantification for linear functionals of the eigenvectors of an unknown low-rank matrix. We prove that this task can be accomplished in a setting where the true matrix is symmetric and the additive noise matrix contains independent (and non-symmetric) entries. Specifically, we develop algorithms that produce confidence intervals for linear forms of individual eigenvectors, based on eigen-decomposition of the asymmetric data matrix followed by a careful de-biasing scheme. The proposed procedures and the accompanying theory enjoy several important features: (1) distribution-free (i.e. prior knowledge about the noise distributions is not needed); (2) adaptive to heteroscedastic noise; (3) statistically optimal under Gaussian noise. Along the way, we establish procedures to construct optimal confidence intervals for the eigenvalues of interest. All this happens under minimal eigenvalue separation, a condition that goes far beyond what generic matrix perturbation theory has to offer. Our studies fall under the category of “fine-grained” functional inference in low-complexity models. |
| Tasks | |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04620v1 |
| https://arxiv.org/pdf/2001.04620v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-for-linear-forms-of-eigenvectors |
| Repo | |
| Framework | |
Triad State Space Construction for Chaotic Signal Classification with Deep Learning
| Title | Triad State Space Construction for Chaotic Signal Classification with Deep Learning |
| Authors | Yadong Zhang, Xin Chen |
| Abstract | Inspired by the well-known permutation entropy (PE), an effective image encoding scheme for chaotic time series, Triad State Space Construction (TSSC), is proposed. The TSSC image can recognize higher-order temporal patterns and identify new forbidden regions in time series motifs beyond the Bandt-Pompe probabilities. The Convolutional Neural Network (ConvNet) is widely used in image classification. The ConvNet classifier based on TSSC images (TSSC-ConvNet) are highly accurate and very robust in the chaotic signal classification. |
| Tasks | Image Classification, Time Series |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.11931v1 |
| https://arxiv.org/pdf/2003.11931v1.pdf | |
| PWC | https://paperswithcode.com/paper/triad-state-space-construction-for-chaotic |
| Repo | |
| Framework | |
Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping
| Title | Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping |
| Authors | Thai Duong, Nikhil Das, Michael Yip, Nikolay Atanasov |
| Abstract | This paper focuses on real-time occupancy mapping and collision checking onboard an autonomous robot navigating in an unknown environment. We propose a new map representation, in which occupied and free space are separated by the decision boundary of a kernel perceptron classifier. We develop an online training algorithm that maintains a very sparse set of support vectors to represent obstacle boundaries in configuration space. We also derive conditions that allow complete (without sampling) collision-checking for piecewise-linear and piecewise-polynomial robot trajectories. We demonstrate the effectiveness of our mapping and collision checking algorithms for autonomous navigation of an Ackermann-drive robot in unknown environments. |
| Tasks | Autonomous Navigation |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01921v1 |
| https://arxiv.org/pdf/2002.01921v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-navigation-in-unknown-environments |
| Repo | |
| Framework | |
Overview of Tools Supporting Planning for Automated Driving
| Title | Overview of Tools Supporting Planning for Automated Driving |
| Authors | Kailin Tong, Zlatan Ajanovic, Georg Stettinger |
| Abstract | Planning is an essential topic in the realm of automated driving. Besides planning algorithms that are widely covered in the literature, planning requires different software tools for its development, validation, and execution. This paper presents a survey of such tools including map representations, communication, traffic rules, open-source planning stacks and middleware, simulation, and visualization tools as well as benchmarks. We start by defining the planning task and different supporting tools. Next, we provide a comprehensive review of state-of-the-art developments and analysis of relations among them. Finally, we discuss the current gaps and suggest future research directions. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04081v1 |
| https://arxiv.org/pdf/2003.04081v1.pdf | |
| PWC | https://paperswithcode.com/paper/overview-of-tools-supporting-planning-for |
| Repo | |
| Framework | |
Deep Object Detection based Mitosis Analysis in Breast Cancer Histopathological Images
| Title | Deep Object Detection based Mitosis Analysis in Breast Cancer Histopathological Images |
| Authors | Anabia Sohail, Muhammad Ahsan Mukhtar, Asifullah Khan, Muhammad Mohsin Zafar, Aneela Zameer, Saranjam Khan |
| Abstract | Empirical evaluation of breast tissue biopsies for mitotic nuclei detection is considered an important prognostic biomarker in tumor grading and cancer progression. However, automated mitotic nuclei detection poses several challenges because of the unavailability of pixel-level annotations, different morphological configurations of mitotic nuclei, their sparse representation, and close resemblance with non-mitotic nuclei. These challenges undermine the precision of the automated detection model and thus make detection difficult in a single phase. This work proposes an end-to-end detection system for mitotic nuclei identification in breast cancer histopathological images. Deep object detection-based Mask R-CNN is adapted for mitotic nuclei detection that initially selects the candidate mitotic region with maximum recall. However, in the second phase, these candidate regions are refined by multi-object loss function to improve the precision. The performance of the proposed detection model shows improved discrimination ability (F-score of 0.86) for mitotic nuclei with significant precision (0.86) as compared to the two-stage detection models (F-score of 0.701) on TUPAC16 dataset. Promising results suggest that the deep object detection-based model has the potential to learn the characteristic features of mitotic nuclei from weakly annotated data and suggests that it can be adapted for the identification of other nuclear bodies in histopathological images. |
| Tasks | Object Detection |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.08803v1 |
| https://arxiv.org/pdf/2003.08803v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-object-detection-based-mitosis-analysis |
| Repo | |
| Framework | |
Extended Feature Pyramid Network for Small Object Detection
| Title | Extended Feature Pyramid Network for Small Object Detection |
| Authors | Chunfang Deng, Mengmeng Wang, Liang Liu, Yong Liu |
| Abstract | Small object detection remains an unsolved challenge because it is hard to extract information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we design a foreground-background-balanced loss function to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100K and small category of general object detection dataset MS COCO. |
| Tasks | Object Detection, Small Object Detection |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07021v1 |
| https://arxiv.org/pdf/2003.07021v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-feature-pyramid-network-for-small |
| Repo | |
| Framework | |
Message Passing for Query Answering over Knowledge Graphs
| Title | Message Passing for Query Answering over Knowledge Graphs |
| Authors | Daniel Daza, Michael Cochez |
| Abstract | Logic-based systems for query answering over knowledge graphs return only answers that rely on information explicitly represented in the graph. To improve recall, recent works have proposed the use of embeddings to predict additional information like missing links, or labels. These embeddings enable scoring entities in the graph as the answer a query, without being fully dependent on the graph structure. In its simplest case, answering a query in such a setting requires predicting a link between two entities. However, link prediction is not sufficient to address complex queries that involve multiple entities and variables. To solve this task, we propose to apply a message passing mechanism to a graph representation of the query, where nodes correspond to variables and entities. This results in an embedding of the query, such that answering entities are close to it in the embedding space. The general formulation of our method allows it to encode a more diverse set of query types in comparison to previous work. We evaluate our method by answering queries that rely on edges not seen during training, obtaining competitive performance. In contrast with previous work, we show that our method can generalize from training for the single-hop, link prediction task, to answering queries with more complex structures. A qualitative analysis reveals that the learned embeddings successfully capture the notion of different entity types. |
| Tasks | Knowledge Graphs, Link Prediction |
| Published | 2020-02-06 |
| URL | https://arxiv.org/abs/2002.02406v1 |
| https://arxiv.org/pdf/2002.02406v1.pdf | |
| PWC | https://paperswithcode.com/paper/message-passing-for-query-answering-over |
| Repo | |
| Framework | |
Wireless 2.0: Towards an Intelligent Radio Environment Empowered by Reconfigurable Meta-Surfaces and Artificial Intelligence
| Title | Wireless 2.0: Towards an Intelligent Radio Environment Empowered by Reconfigurable Meta-Surfaces and Artificial Intelligence |
| Authors | Haris Gacanin, Marco Di Renzo |
| Abstract | We introduce “Wireless 2.0”: The future generation of wireless communication networks, where the radio environment becomes controllable, programmable, and intelligent by leveraging the emerging technologies of reconfigurable metasurfaces and artificial intelligence (AI). This paper, in particular, puts the emphasis on AI-based computational methods and commence with an overview of the concept of intelligent radio environments based on reconfigurable meta-surfaces. Later we elaborate on data management aspects, the requirements of supervised learning by examples, and the paradigm of reinforcement learning (RL) to learn by acting. Finally, we highlight numerous open challenges and research directions. |
| Tasks | |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.11040v1 |
| https://arxiv.org/pdf/2002.11040v1.pdf | |
| PWC | https://paperswithcode.com/paper/wireless-20-towards-an-intelligent-radio |
| Repo | |
| Framework | |
Unique Geometry and Texture from Corresponding Image Patches
| Title | Unique Geometry and Texture from Corresponding Image Patches |
| Authors | Dor Verbin, Steven J. Gortler, Todd Zickler |
| Abstract | We present a sufficient condition for the recovery of a unique texture process and a unique set of viewpoints from a set of image patches that are generated by observing a flat texture process from unknown directions and orientations. We show that four image patches are sufficient in general, and we characterize the ambiguities that arise when this condition is not satisfied. The results are applicable to the perception of shape from texture and to texture-based structure from motion. |
| Tasks | |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08885v1 |
| https://arxiv.org/pdf/2003.08885v1.pdf | |
| PWC | https://paperswithcode.com/paper/unique-geometry-and-texture-from |
| Repo | |
| Framework | |
Planning for Compilation of a Quantum Algorithm for Graph Coloring
| Title | Planning for Compilation of a Quantum Algorithm for Graph Coloring |
| Authors | Minh Do, Zhihui Wang, Bryan O’Gorman, Davide Venturelli, Eleanor Rieffel, Jeremy Frank |
| Abstract | The problem of compiling general quantum algorithms for implementation on near-term quantum processors has been introduced to the AI community. Previous work demonstrated that temporal planning is an attractive approach for part of this compilationtask, specifically, the routing of circuits that implement the Quantum Alternating Operator Ansatz (QAOA) applied to the MaxCut problem on a quantum processor architecture. In this paper, we extend the earlier work to route circuits that implement QAOA for Graph Coloring problems. QAOA for coloring requires execution of more, and more complex, operations on the chip, which makes routing a more challenging problem. We evaluate the approach on state-of-the-art hardware architectures from leading quantum computing companies. Additionally, we apply a planning approach to qubit initialization. Our empirical evaluation shows that temporal planning compares well to reasonable analytic upper bounds, and that solving qubit initialization with a classical planner generally helps temporal planners in finding shorter-makespan compilations for QAOA for Graph Coloring. These advances suggest that temporal planning can be an effective approach for more complex quantum computing algorithms and architectures. |
| Tasks | |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.10917v1 |
| https://arxiv.org/pdf/2002.10917v1.pdf | |
| PWC | https://paperswithcode.com/paper/planning-for-compilation-of-a-quantum |
| Repo | |
| Framework | |
From Algebraic Word Problem to Program: A Formalized Approach
| Title | From Algebraic Word Problem to Program: A Formalized Approach |
| Authors | Adam Wiemerslage, Shafiuddin Rehan Ahmed |
| Abstract | In this paper, we propose a pipeline to convert grade school level algebraic word problem into program of a formal languageA-IMP. Using natural language processing tools, we break the problem into sentence fragments which can then be reduced to functions. The functions are categorized by the head verb of the sentence and its structure, as defined by (Hosseini et al., 2014). We define the function signature and extract its arguments from the text using dependency parsing. We have a working implementation of the entire pipeline which can be found on our github repository. |
| Tasks | Dependency Parsing |
| Published | 2020-03-11 |
| URL | https://arxiv.org/abs/2003.11517v1 |
| https://arxiv.org/pdf/2003.11517v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-algebraic-word-problem-to-program-a |
| Repo | |
| Framework | |
Shallow Encoder Deep Decoder (SEDD) Networks for Image Encryption and Decryption
| Title | Shallow Encoder Deep Decoder (SEDD) Networks for Image Encryption and Decryption |
| Authors | Chirag Gupta |
| Abstract | This paper explores a new framework for lossy image encryption and decryption using a simple shallow encoder neural network E for encryption, and a complex deep decoder neural network D for decryption. E is kept simple so that encoding can be done on low power and portable devices and can in principle be any nonlinear function which outputs an encoded vector. D is trained to decode the encodings using the dataset of image - encoded vector pairs obtained from E and happens independently of E. As the encodings come from E which while being a simple neural network, still has thousands of random parameters and therefore the encodings would be practically impossible to crack without D. This approach differs from autoencoders as D is trained completely independently of E, although the structure may seem similar. Therefore, this paper also explores empirically if a deep neural network can learn to reconstruct the original data in any useful form given the output of a neural network or any other nonlinear function, which can have very useful applications in Cryptanalysis. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the decoded images from D along with some limitations. |
| Tasks | Cryptanalysis |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.03017v1 |
| https://arxiv.org/pdf/2001.03017v1.pdf | |
| PWC | https://paperswithcode.com/paper/shallow-encoder-deep-decoder-sedd-networks |
| Repo | |
| Framework | |
Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant
| Title | Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant |
| Authors | Shayan Aziznejad, Harshit Gupta, Joaquim Campos, Michael Unser |
| Abstract | We introduce a variational framework to learn the activation functions of deep neural networks. The main motivation is to control the Lipschitz regularity of the input-output relation. To that end, we first establish a global bound for the Lipschitz constant of neural networks. Based on the obtained bound, we then formulate a variational problem for learning activation functions. Our variational problem is infinite-dimensional and is not computationally tractable. However, we prove that there always exists a solution that has continuous and piecewise-linear (linear-spline) activations. This reduces the original problem to a finite-dimensional minimization. We numerically compare our scheme with standard ReLU network and its variations, PReLU and LeakyReLU. |
| Tasks | |
| Published | 2020-01-17 |
| URL | https://arxiv.org/abs/2001.06263v1 |
| https://arxiv.org/pdf/2001.06263v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-networks-with-trainable |
| Repo | |
| Framework | |
