Paper Group ANR 1405
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction. Generative Design in Minecraft: Chronicle Challenge. Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal. Learning-based real-time method to looking through scattering medium beyond the memory effect. Multi-Agent Path Finding with Capacity Constraints. …
Multi-Level Composite Stochastic Optimization via Nested Variance Reduction
| Title | Multi-Level Composite Stochastic Optimization via Nested Variance Reduction |
| Authors | Junyu Zhang, Lin Xiao |
| Abstract | We consider multi-level composite optimization problems where each mapping in the composition is the expectation over a family of random smooth mappings or the sum of some finite number of smooth mappings. We present a normalized proximal approximate gradient (NPAG) method where the approximate gradients are obtained via nested stochastic variance reduction. In order to find an approximate stationary point where the expected norm of its gradient mapping is less than $\epsilon$, the total sample complexity of our method is $O(\epsilon^{-3})$ in the expectation case, and $O(N+\sqrt{N}\epsilon^{-2})$ in the finite-sum case where $N$ is the total number of functions across all composition levels. In addition, the dependence of our total sample complexity on the number of composition levels is polynomial, rather than exponential as in previous work. |
| Tasks | Stochastic Optimization |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11468v1 |
| https://arxiv.org/pdf/1908.11468v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-composite-stochastic-optimization |
| Repo | |
| Framework | |
Generative Design in Minecraft: Chronicle Challenge
| Title | Generative Design in Minecraft: Chronicle Challenge |
| Authors | Christoph Salge, Christian Guckelsberger, Michael Cerny Green, Rodrigo Canaan, Julian Togelius |
| Abstract | We introduce the Chronicle Challenge as an optional addition to the Settlement Generation Challenge in Minecraft. One of the foci of the overall competition is adaptive procedural content generation (PCG), an arguably under-explored problem in computational creativity. In the base challenge, participants must generate new settlements that respond to and ideally interact with existing content in the world, such as the landscape or climate. The goal is to understand the underlying creative process, and to design better PCG systems. The Chronicle Challenge in particular focuses on the generation of a narrative based on the history of a generated settlement, expressed in natural language. We discuss the unique features of the Chronicle Challenge in comparison to other competitions, clarify the characteristics of a chronicle eligible for submission and describe the evaluation criteria. We furthermore draw on simulation-based approaches in computational storytelling as examples to how this challenge could be approached. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05888v1 |
| https://arxiv.org/pdf/1905.05888v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-design-in-minecraft-chronicle |
| Repo | |
| Framework | |
Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal
| Title | Bilinear Constraint based ADMM for Mixed Poisson-Gaussian Noise Removal |
| Authors | Jie Zhang, Yuping Duan, Yue Lu, Michael K. Ng, Huibin Chang |
| Abstract | In this paper, we propose new operator-splitting algorithms for the total variation regularized infimal convolution (TV-IC) model [4] in order to remove mixed Poisson-Gaussian(MPG) noise. In the existing splitting algorithm for TV-IC, an inner loop by Newton method had to be adopted for one nonlinear optimization subproblem, which increased the computation cost per outer loop. By introducing a new bilinear constraint and applying the alternating direction method of multipliers (ADMM), all subproblems of the proposed algorithms named as BCA (short for Bilinear Constraint based ADMM algorithm) and BCAf(short for a variant of BCA with fully splitting form) can be very efficiently solved; especially for the proposed BCAf, they can be calculated without any inner iterations. Under mild conditions, the convergence of the proposed BCA is investigated. Numerically, compared to existing primal-dual algorithms for the TV-IC model, the proposed algorithms, with fewer tunable parameters, converge much faster and produce comparable results meanwhile. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08206v2 |
| https://arxiv.org/pdf/1910.08206v2.pdf | |
| PWC | https://paperswithcode.com/paper/bilinear-constraint-based-admm-for-mixed |
| Repo | |
| Framework | |
Learning-based real-time method to looking through scattering medium beyond the memory effect
| Title | Learning-based real-time method to looking through scattering medium beyond the memory effect |
| Authors | Enlai Guo, Shuo Zhu, Yan Sun, Lianfa Bai, Jing Han |
| Abstract | Strong scattering medium brings great difficulties to optical imaging, which is also a problem in medical imaging and many other fields. Optical memory effect makes it possible to image through strong random scattering medium. However, this method also has the limitation of limited angle field-of-view (FOV), which prevents it from being applied in practice. In this paper, a kind of practical convolutional neural network called PDSNet is proposed, which effectively breaks through the limitation of optical memory effect on FOV. Experiments is conducted to prove that the scattered pattern can be reconstructed accurately in real-time by PDSNet, and it is widely applicable to retrieve complex objects of random scales and different scattering media. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.11272v2 |
| https://arxiv.org/pdf/1910.11272v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-real-time-method-to-looking |
| Repo | |
| Framework | |
Multi-Agent Path Finding with Capacity Constraints
| Title | Multi-Agent Path Finding with Capacity Constraints |
| Authors | Pavel Surynek, T. K. Satish Kumar, Sven Koenig |
| Abstract | In multi-agent path finding (MAPF) the task is to navigate agents from their starting positions to given individual goals. The problem takes place in an undirected graph whose vertices represent positions and edges define the topology. Agents can move to neighbor vertices across edges. In the standard MAPF, space occupation by agents is modeled by a capacity constraint that permits at most one agent per vertex. We suggest an extension of MAPF in this paper that permits more than one agent per vertex. Propositional satisfiability (SAT) models for these extensions of MAPF are studied. We focus on modeling capacity constraints in SAT-based formulations of MAPF and evaluation of performance of these models. We extend two existing SAT-based formulations with vertex capacity constraints: MDD-SAT and SMT-CBS where the former is an approach that builds the model in an eager way while the latter relies on lazy construction of the model. |
| Tasks | Multi-Agent Path Finding |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.12648v1 |
| https://arxiv.org/pdf/1907.12648v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-path-finding-with-capacity |
| Repo | |
| Framework | |
Low Complexity Autoencoder based End-to-End Learning of Coded Communications Systems
| Title | Low Complexity Autoencoder based End-to-End Learning of Coded Communications Systems |
| Authors | Nuwanthika Rajapaksha, Nandana Rajatheva, Matti Latva-aho |
| Abstract | End-to-end learning of a communications system using the deep learning-based autoencoder concept has drawn interest in recent research due to its simplicity, flexibility and its potential of adapting to complex channel models and practical system imperfections. In this paper, we have compared the bit error rate (BER) performance of autoencoder based systems and conventional channel coded systems with convolutional coding (CC), in order to understand the potential of deep learning-based systems as alternatives to conventional systems. From the simulations, autoencoder implementation was observed to have a better BER in 0-5 dB $E_{b}/N_{0}$ range than its equivalent half-rate convolutional coded BPSK with hard decision decoding, and to have only less than 1 dB gap at a BER of $10^{-5}$. Furthermore, we have also proposed a novel low complexity autoencoder architecture to implement end-to-end learning of coded systems in which we have shown better BER performance than the baseline implementation. The newly proposed low complexity autoencoder was capable of achieving a better BER performance than half-rate 16-QAM with hard decision decoding over the full 0-10 dB $E_{b}/N_{0}$ range and a better BER performance than the soft decision decoding in 0-4 dB $E_{b}/N_{0}$ range. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08009v2 |
| https://arxiv.org/pdf/1911.08009v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-complexity-autoencoder-based-end-to-end |
| Repo | |
| Framework | |
Exploiting a Stimuli Encoding Scheme of Spiking Neural Networks for Stream Learning
| Title | Exploiting a Stimuli Encoding Scheme of Spiking Neural Networks for Stream Learning |
| Authors | Jesus L. Lobo, Izaskun Oregi, Albert Bifet, Javier Del Ser |
| Abstract | Stream data processing has gained progressive momentum with the arriving of new stream applications and big data scenarios. One of the most promising techniques in stream learning is the Spiking Neural Network, and some of them use an interesting population encoding scheme to transform the incoming stimuli into spikes. This study sheds lights on the key issue of this encoding scheme, the Gaussian receptive fields, and focuses on applying them as a pre-processing technique to any dataset in order to gain representativeness, and to boost the predictive performance of the stream learning methods. Experiments with synthetic and real data sets are presented, and lead to confirm that our approach can be applied successfully as a general pre-processing technique in many real cases. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1908.08018v1 |
| https://arxiv.org/pdf/1908.08018v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-a-stimuli-encoding-scheme-of |
| Repo | |
| Framework | |
Mining Twitter to Assess the Determinants of Health Behavior towards Human Papillomavirus Vaccination in the United States
| Title | Mining Twitter to Assess the Determinants of Health Behavior towards Human Papillomavirus Vaccination in the United States |
| Authors | Hansi Zhang, Christopher Wheldon, Adam G. Dunn, Cui Tao, Jinhai Huo, Rui Zhang, Mattia Prosperi, Yi Guo, Jiang Bian |
| Abstract | Objectives To test the feasibility of using Twitter data to assess determinants of consumers’ health behavior towards Human papillomavirus (HPV) vaccination informed by the Integrated Behavior Model (IBM). Methods We used three Twitter datasets spanning from 2014 to 2018. We preprocessed and geocoded the tweets, and then built a rule-based model that classified each tweet into either promotional information or consumers’ discussions. We applied topic modeling to discover major themes, and subsequently explored the associations between the topics learned from consumers’ discussions and the responses of HPV-related questions in the Health Information National Trends Survey (HINTS). Results We collected 2,846,495 tweets and analyzed 335,681 geocoded tweets. Through topic modeling, we identified 122 high-quality topics. The most discussed consumer topic is “cervical cancer screening”; while in promotional tweets, the most popular topic is to increase awareness of “HPV causes cancer”. 87 out of the 122 topics are correlated between promotional information and consumers’ discussions. Guided by IBM, we examined the alignment between our Twitter findings and the results obtained from HINTS. 35 topics can be mapped to HINTS questions by keywords, 112 topics can be mapped to IBM constructs, and 45 topics have statistically significant correlations with HINTS responses in terms of geographic distributions. Conclusion Not only mining Twitter to assess consumers’ health behaviors can obtain results comparable to surveys but can yield additional insights via a theory-driven approach. Limitations exist, nevertheless, these encouraging results impel us to develop innovative ways of leveraging social media in the changing health communication landscape. |
| Tasks | |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.11624v1 |
| https://arxiv.org/pdf/1907.11624v1.pdf | |
| PWC | https://paperswithcode.com/paper/mining-twitter-to-assess-the-determinants-of |
| Repo | |
| Framework | |
LSTM vs. GRU vs. Bidirectional RNN for script generation
| Title | LSTM vs. GRU vs. Bidirectional RNN for script generation |
| Authors | Sanidhya Mangal, Poorva Joshi, Rahul Modak |
| Abstract | Scripts are an important part of any TV series. They narrate movements, actions and expressions of characters. In this paper, a case study is presented on how different sequence to sequence deep learning models perform in the task of generating new conversations between characters as well as new scenarios on the basis of a script (previous conversations). A comprehensive comparison between these models, namely, LSTM, GRU and Bidirectional RNN is presented. All the models are designed to learn the sequence of recurring characters from the input sequence. Each input sequence will contain, say “n” characters, and the corresponding targets will contain the same number of characters, except, they will be shifted one character to the right. In this manner, input and output sequences are generated and used to train the models. A closer analysis of explored models performance and efficiency is delineated with the help of graph plots and generated texts by taking some input string. These graphs describe both, intraneural performance and interneural model performance for each model. |
| Tasks | |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04332v1 |
| https://arxiv.org/pdf/1908.04332v1.pdf | |
| PWC | https://paperswithcode.com/paper/lstm-vs-gru-vs-bidirectional-rnn-for-script |
| Repo | |
| Framework | |
Algorithms for Grey-Weighted Distance Computations
| Title | Algorithms for Grey-Weighted Distance Computations |
| Authors | Magnus Gedda |
| Abstract | With the increasing size of datasets and demand for real time response for interactive applications, improving runtime for algorithms with excessive computational requirements has become increasingly important. Many different algorithms combining efficient priority queues with various helper structures have been proposed for computing grey-weighted distance transforms. Here we compare the performance of popular competitive algorithms in different scenarios to form practical guidelines easy to adopt. The label-setting category of algorithms is shown to be the best choice for all scenarios. The hierarchical heap with a pointer array to keep track of nodes on the heap is shown to be the best choice as priority queue. However, if memory is a critical issue, then the best choice is the Dial priority queue for integer valued costs and the Untidy priority queue for real valued costs. |
| Tasks | |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03017v1 |
| https://arxiv.org/pdf/1905.03017v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-grey-weighted-distance |
| Repo | |
| Framework | |
Interactive Collaborative Exploration using Incomplete Contexts
| Title | Interactive Collaborative Exploration using Incomplete Contexts |
| Authors | Maximilian Felde, Gerd Stumme |
| Abstract | A well-known knowledge acquisition method in the field of Formal Concept Analysis (FCA) is attribute exploration. It is used to reveal dependencies in a set of attributes with help of a domain expert. In most applications no single expert is capable (time- and knowledge-wise) of exploring the knowledge domain alone. However, there is up to now no theory that models the interaction of multiple experts for the task of attribute exploration with incomplete knowledge. To this end, we to develop a theoretical framework that allows multiple experts to explore domains together. We use a representation of incomplete knowledge as three-valued contexts. We then adapt the corresponding version of attribute exploration to fit the setting of multiple experts. We suggest formalizations for key components like expert knowledge, interaction and collaboration strategy. In particular, we define an order that allows to compare the results of different exploration strategies on the same task with respect to their information completeness. Furthermore we discuss other ways of comparing collaboration strategies and suggest avenues for future research. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08740v2 |
| https://arxiv.org/pdf/1908.08740v2.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-collaborative-exploration-using |
| Repo | |
| Framework | |
Learning Programmatically Structured Representations with Perceptor Gradients
| Title | Learning Programmatically Structured Representations with Perceptor Gradients |
| Authors | Svetlin Penkov, Subramanian Ramamoorthy |
| Abstract | We present the perceptor gradients algorithm – a novel approach to learning symbolic representations based on the idea of decomposing an agent’s policy into i) a perceptor network extracting symbols from raw observation data and ii) a task encoding program which maps the input symbols to output actions. We show that the proposed algorithm is able to learn representations that can be directly fed into a Linear-Quadratic Regulator (LQR) or a general purpose A* planner. Our experimental results confirm that the perceptor gradients algorithm is able to efficiently learn transferable symbolic representations as well as generate new observations according to a semantically meaningful specification. |
| Tasks | |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00956v1 |
| https://arxiv.org/pdf/1905.00956v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-programmatically-structured-1 |
| Repo | |
| Framework | |
Machine Learning for Prediction with Missing Dynamics
| Title | Machine Learning for Prediction with Missing Dynamics |
| Authors | John Harlim, Shixiao W. Jiang, Senwei Liang, Haizhao Yang |
| Abstract | This article presents a general framework for recovering missing dynamical systems using available data and machine learning techniques. The proposed framework reformulates the prediction problem as a supervised learning problem to approximate a map that takes the memories of the resolved and identifiable unresolved variables to the missing components in the resolved dynamics. We demonstrate the effectiveness of the proposed framework with a theoretical guarantee of a path-wise convergence of the resolved variables up to finite time and numerical tests on prototypical models in various scientific domains. These include the 57-mode barotropic stress models with multiscale interactions that mimic the blocked and unblocked patterns observed in the atmosphere, the nonlinear Schr"{o}dinger equation which found many applications in physics such as optics and Bose-Einstein-Condense, the Kuramoto-Sivashinsky equation which spatiotemporal chaotic pattern formation models trapped ion mode in plasma and phase dynamics in reaction-diffusion systems. While many machine learning techniques can be used to validate the proposed framework, we found that recurrent neural networks outperform kernel regression methods in terms of recovering the trajectory of the resolved components and the equilibrium one-point and two-point statistics. This superb performance suggests that recurrent neural networks are an effective tool for recovering the missing dynamics that involves approximation of high-dimensional functions. |
| Tasks | |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.05861v2 |
| https://arxiv.org/pdf/1910.05861v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-prediction-with-missing |
| Repo | |
| Framework | |
Disentangling Content and Style via Unsupervised Geometry Distillation
| Title | Disentangling Content and Style via Unsupervised Geometry Distillation |
| Authors | Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy |
| Abstract | It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably. It is rare for one to have access to a large number of data to help separate the influences. In this paper, we present a novel framework to learn this disentangled representation in a completely unsupervised manner. We address this problem in a two-branch Autoencoder framework. For the structural content branch, we project the latent factor into a soft structured point tensor and constrain it with losses derived from prior knowledge. This constraint encourages the branch to distill geometry information. Another branch learns the complementary style information. The two branches form an effective framework that can disentangle object’s content-style representation without any human annotation. We evaluate our approach on four image datasets, on which we demonstrate the superior disentanglement and visual analogy quality both in synthesized and real-world data. We are able to generate photo-realistic images with 256*256 resolution that are clearly disentangled in content and style. |
| Tasks | |
| Published | 2019-05-11 |
| URL | https://arxiv.org/abs/1905.04538v1 |
| https://arxiv.org/pdf/1905.04538v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-content-and-style-via |
| Repo | |
| Framework | |
Enriched Mixtures of Gaussian Process Experts
| Title | Enriched Mixtures of Gaussian Process Experts |
| Authors | Charles W. L. Gadd, Sara Wade, Alexis Boukouvalas |
| Abstract | Mixtures of experts probabilistically divide the input space into regions, where the assumptions of each expert, or conditional model, need only hold locally. Combined with Gaussian process (GP) experts, this results in a powerful and highly flexible model. We focus on alternative mixtures of GP experts, which model the joint distribution of the inputs and targets explicitly. We highlight issues of this approach in multi-dimensional input spaces, namely, poor scalability and the need for an unnecessarily large number of experts, degrading the predictive performance and increasing uncertainty. We construct a novel model to address these issues through a nested partitioning scheme that automatically infers the number of components at both levels. Multiple response types are accommodated through a generalised GP framework, while multiple input types are included through a factorised exponential family structure. We show the effectiveness of our approach in estimating a parsimonious probabilistic description of both synthetic data of increasing dimension and an Alzheimer’s challenge dataset. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12969v1 |
| https://arxiv.org/pdf/1905.12969v1.pdf | |
| PWC | https://paperswithcode.com/paper/enriched-mixtures-of-gaussian-process-experts |
| Repo | |
| Framework | |
