Paper Group ANR 1749
New Risk Bounds for 2D Total Variation Denoising. Asynchronous “Events” are Better For Motion Estimation. Machine-learned metrics for predicting the likelihood of success in materials discovery. Delegative Reinforcement Learning: learning to avoid traps with a little help. On the Possibility of Rewarding Structure Learning Agents: Mutual Informatio …
New Risk Bounds for 2D Total Variation Denoising
| Title | New Risk Bounds for 2D Total Variation Denoising |
| Authors | Sabyasachi Chatterjee, Subhajit Goswami |
| Abstract | 2D Total Variation Denoising (TVD) is a widely used technique for image denoising. It is also an important non parametric regression method for estimating functions with heterogenous smoothness. Recent results have shown the TVD estimator to be nearly minimax rate optimal for the class of functions with bounded variation. In this paper, we complement these worst case guarantees by investigating the adaptivity of the TVD estimator to functions which are piecewise constant on axis aligned rectangles. We rigorously show that, when the truth is piecewise constant, the ideally tuned TVD estimator performs better than in the worst case. We also study the issue of choosing the tuning parameter. In particular, we propose a fully data driven version of the TVD estimator which enjoys similar worst case risk guarantees as the ideally tuned TVD estimator. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01215v3 |
| https://arxiv.org/pdf/1902.01215v3.pdf | |
| PWC | https://paperswithcode.com/paper/new-risk-bounds-for-2d-total-variation |
| Repo | |
| Framework | |
Asynchronous “Events” are Better For Motion Estimation
| Title | Asynchronous “Events” are Better For Motion Estimation |
| Authors | Yuhu Guo, Han Xiao, Yidong Chen, Xiaodong Shi |
| Abstract | Event-based camera is a bio-inspired vision sensor that records intensity changes (called event) asynchronously in each pixel. As an instance of event-based camera, Dynamic and Active-pixel Vision Sensor (DAVIS) combines a standard camera and an event-based camera. However, traditional models could not deal with the event stream asynchronously. To analyze the event stream asynchronously, most existing approaches accumulate events within a certain time interval and treat the accumulated events as a synchronous frame, which wastes the intensity change information and weakens the advantages of DAVIS. Therefore, in this paper, we present the first neural asynchronous approach to process event stream for event-based camera. Our method asynchronously extracts dynamic information from events by leveraging previous motion and critical features of gray-scale frames. To our best knowledge, this is the first neural asynchronous method to analyze event stream through a novel deep neural network. Extensive experiments demonstrate that our proposed model achieves remarkable improvements against the state-of-the-art baselines. |
| Tasks | Motion Estimation |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1904.11578v1 |
| http://arxiv.org/pdf/1904.11578v1.pdf | |
| PWC | https://paperswithcode.com/paper/asynchronous-events-are-better-for-motion |
| Repo | |
| Framework | |
Machine-learned metrics for predicting the likelihood of success in materials discovery
| Title | Machine-learned metrics for predicting the likelihood of success in materials discovery |
| Authors | Yoolhee Kim, Edward Kim, Erin Antono, Bryce Meredig, Julia Ling |
| Abstract | Materials discovery is often compared to the challenge of finding a needle in a haystack. While much work has focused on accurately predicting the properties of candidate materials with machine learning (ML), which amounts to evaluating whether a given candidate is a piece of straw or a needle, less attention has been paid to a critical question: Are we searching in the right haystack? We refer to the haystack as the design space for a particular materials discovery problem (i.e. the set of possible candidate materials to synthesize), and thus frame this question as one of design space selection. In this paper, we introduce two metrics, the Predicted Fraction of Improved Candidates (PFIC), and the Cumulative Maximum Likelihood of Improvement (CMLI), which we demonstrate can identify discovery-rich and discovery-poor design spaces, respectively. Using CMLI and PFIC together to identify optimal design spaces can significantly accelerate ML-driven materials discovery. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11201v2 |
| https://arxiv.org/pdf/1911.11201v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learned-metrics-for-predicting |
| Repo | |
| Framework | |
Delegative Reinforcement Learning: learning to avoid traps with a little help
| Title | Delegative Reinforcement Learning: learning to avoid traps with a little help |
| Authors | Vanessa Kosoy |
| Abstract | Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an external advisor. We thus arrive at a setting of active one-shot model-based reinforcement learning that we call DRL (delegative reinforcement learning.) The algorithm we construct in order to demonstrate the regret bound is a variant of Posterior Sampling Reinforcement Learning supplemented by a subroutine that decides which actions should be delegated. The algorithm is not anytime, since the parameters must be adjusted according to the target time discount. Currently, our analysis is limited to Markov decision processes with finite numbers of hypotheses, states and actions. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08461v1 |
| https://arxiv.org/pdf/1907.08461v1.pdf | |
| PWC | https://paperswithcode.com/paper/delegative-reinforcement-learning-learning-to |
| Repo | |
| Framework | |
On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets
| Title | On the Possibility of Rewarding Structure Learning Agents: Mutual Information on Linguistic Random Sets |
| Authors | Ignacio Arroyo-Fernández, Mauricio Carrasco-Ruíz, J. Anibal Arias-Aguilar |
| Abstract | We present a first attempt to elucidate a theoretical and empirical approach to design the reward provided by a natural language environment to some structure learning agent. To this end, we revisit the Information Theory of unsupervised induction of phrase-structure grammars to characterize the behavior of simulated actions modeled as set-valued random variables (random sets of linguistic samples) constituting semantic structures. Our results showed empirical evidence of that simulated semantic structures (Open Information Extraction triplets) can be distinguished from randomly constructed ones by observing the Mutual Information among their constituents. This suggests the possibility of rewarding structure learning agents without using pretrained structural analyzers (oracle actors/experts). |
| Tasks | Open Information Extraction |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04023v4 |
| https://arxiv.org/pdf/1910.04023v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-possibility-of-rewarding-structure |
| Repo | |
| Framework | |
Coevo: a collaborative design platform with artificial agents
| Title | Coevo: a collaborative design platform with artificial agents |
| Authors | Gerard Serra, David Miralles |
| Abstract | We present Coevo, an online platform that allows both humans and artificial agents to design shapes that solve different tasks. Our goal is to explore common shared design tools that can be used by humans and artificial agents in a context of creation. This approach can provide a better knowledge transfer and interaction with artificial agents since a common language of design is defined. In this paper, we outline the main components of this platform and discuss the definition of a human-centered language to enhance human-AI collaboration in co-creation scenarios. |
| Tasks | Transfer Learning |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13333v1 |
| http://arxiv.org/pdf/1904.13333v1.pdf | |
| PWC | https://paperswithcode.com/paper/coevo-a-collaborative-design-platform-with |
| Repo | |
| Framework | |
Learning New Tricks from Old Dogs – Inter-Species, Inter-Tissue Domain Adaptation for Mitotic Figure Assessment
| Title | Learning New Tricks from Old Dogs – Inter-Species, Inter-Tissue Domain Adaptation for Mitotic Figure Assessment |
| Authors | Marc Aubreville, Christof A. Bertram, Samir Jabari, Christian Marzahl, Robert Klopfleisch, Andreas Maier |
| Abstract | For histopathological tumor assessment, the count of mitotic figures per area is an important part of prognostication. Algorithmic approaches - such as for mitotic figure identification - have significantly improved in recent times, potentially allowing for computer-augmented or fully automatic screening systems in the future. This trend is further supported by whole slide scanning microscopes becoming available in many pathology labs and could soon become a standard imaging tool. For an application in broader fields of such algorithms, the availability of mitotic figure data sets of sufficient size for the respective tissue type and species is an important precondition, that is, however, rarely met. While algorithmic performance climbed steadily for e.g. human mammary carcinoma, thanks to several challenges held in the field, for most tumor types, data sets are not available. In this work, we assess domain transfer of mitotic figure recognition using domain adversarial training on four data sets, two from dogs and two from humans. We were able to show that domain adversarial training considerably improves accuracy when applying mitotic figure classification learned from the canine on the human data sets (up to +12.8% in accuracy) and is thus a helpful method to transfer knowledge from existing data sets to new tissue types and species. |
| Tasks | Domain Adaptation |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10873v1 |
| https://arxiv.org/pdf/1911.10873v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-new-tricks-from-old-dogs-inter |
| Repo | |
| Framework | |
Evolution of Cooperation for Multiple Mutant Configurations on All Regular Graphs with $N \leq 14$ players
| Title | Evolution of Cooperation for Multiple Mutant Configurations on All Regular Graphs with $N \leq 14$ players |
| Authors | Hendrik Richter |
| Abstract | We study the emergence of cooperation in structured populations with any arrangement of cooperators and defectors on the evolutionary graph. Using structure coefficients defined for configurations describing such arrangements of any number of mutants, we provide results for weak selection to favor cooperation over defection on any regular graph with $N \leq 14$ vertices. Furthermore, the properties of graphs that particularly promote cooperation are analyzed. It is shown that the number of graph cycles of certain length is a good predictor for the values of the structure coefficient, and thus a tendency to favor cooperation. Another property of particularly cooperation-promoting regular graphs with a low degree is that they are structured to have blocks with clusters of mutants that are connected by cut vertices and/or hinge vertices. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03710v1 |
| https://arxiv.org/pdf/1911.03710v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolution-of-cooperation-for-multiple-mutant |
| Repo | |
| Framework | |
Synthesis of Boolean Networks from Biological Dynamical Constraints using Answer-Set Programming
| Title | Synthesis of Boolean Networks from Biological Dynamical Constraints using Answer-Set Programming |
| Authors | Stéphanie Chevalier, Christine Froidevaux, Loïc Paulevé, Andrei Zinovyev |
| Abstract | Boolean networks model finite discrete dynamical systems with complex behaviours. The state of each component is determined by a Boolean function of the state of (a subset of) the components of the network. This paper addresses the synthesis of these Boolean functions from constraints on their domain and emerging dynamical properties of the resulting network. The dynamical properties relate to the existence and absence of trajectories between partially observed configurations, and to the stable behaviours (fixpoints and cyclic attractors). The synthesis is expressed as a Boolean satisfiability problem relying on Answer-Set Programming with a parametrized complexity, and leads to a complete non-redundant characterization of the set of solutions. Considered constraints are particularly suited to address the synthesis of models of cellular differentiation processes, as illustrated on a case study. The scalability of the approach is demonstrated on random networks with scale-free structures up to 100 to 1,000 nodes depending on the type of constraints. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04309v2 |
| https://arxiv.org/pdf/1909.04309v2.pdf | |
| PWC | https://paperswithcode.com/paper/synthesis-of-boolean-networks-from-biological |
| Repo | |
| Framework | |
Improving Deep Neuroevolution via Deep Innovation Protection
| Title | Improving Deep Neuroevolution via Deep Innovation Protection |
| Authors | Sebastian Risi, Kenneth O. Stanley |
| Abstract | Evolutionary-based optimization approaches have recently shown promising results in domains such as Atari and robot locomotion but less so in solving 3D tasks directly from pixels. This paper presents a method called Deep Innovation Protection (DIP) that allows training complex world models end-to-end for such 3D environments. The main idea behind the approach is to employ multiobjective optimization to temporally reduce the selection pressure on specific components in a world model, allowing other components to adapt. We investigate the emergent representations of these evolved networks, which learn a model of the world without the need for a specific forward-prediction loss. |
| Tasks | Multiobjective Optimization |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.01683v1 |
| https://arxiv.org/pdf/2001.01683v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-deep-neuroevolution-via-deep |
| Repo | |
| Framework | |
Multi-Component Graph Convolutional Collaborative Filtering
| Title | Multi-Component Graph Convolutional Collaborative Filtering |
| Authors | Xiao Wang, Ruijia Wang, Chuan Shi, Guojie Song, Qingyong Li |
| Abstract | The interactions of users and items in recommender system could be naturally modeled as a user-item bipartite graph. In recent years, we have witnessed an emerging research effort in exploring user-item graph for collaborative filtering methods. Nevertheless, the formation of user-item interactions typically arises from highly complex latent purchasing motivations, such as high cost performance or eye-catching appearance, which are indistinguishably represented by the edges. The existing approaches still remain the differences between various purchasing motivations unexplored, rendering the inability to capture fine-grained user preference. Therefore, in this paper we propose a novel Multi-Component graph convolutional Collaborative Filtering (MCCF) approach to distinguish the latent purchasing motivations underneath the observed explicit user-item interactions. Specifically, there are two elaborately designed modules, decomposer and combiner, inside MCCF. The former first decomposes the edges in user-item graph to identify the latent components that may cause the purchasing relationship; the latter then recombines these latent components automatically to obtain unified embeddings for prediction. Furthermore, the sparse regularizer and weighted random sample strategy are utilized to alleviate the overfitting problem and accelerate the optimization. Empirical results on three real datasets and a synthetic dataset not only show the significant performance gains of MCCF, but also well demonstrate the necessity of considering multiple components. |
| Tasks | Recommendation Systems |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10699v1 |
| https://arxiv.org/pdf/1911.10699v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-component-graph-convolutional |
| Repo | |
| Framework | |
Diagnosing model misspecification and performing generalized Bayes’ updates via probabilistic classifiers
| Title | Diagnosing model misspecification and performing generalized Bayes’ updates via probabilistic classifiers |
| Authors | Owen Thomas, Jukka Corander |
| Abstract | Model misspecification is a long-standing enigma of the Bayesian inference framework as posteriors tend to get overly concentrated on ill-informed parameter values towards the large sample limit. Tempering of the likelihood has been established as a safer way to do updates from prior to posterior in the presence of model misspecification. At one extreme tempering can ignore the data altogether and at the other extreme it provides the standard Bayes’ update when no misspecification is assumed to be present. However, it is an open issue how to best recognize misspecification and choose a suitable level of tempering without access to the true generating model. Here we show how probabilistic classifiers can be employed to resolve this issue. By training a probabilistic classifier to discriminate between simulated and observed data provides an estimate of the ratio between the model likelihood and the likelihood of the data under the unobserved true generative process, within the discriminatory abilities of the classifier. The expectation of the logarithm of a ratio with respect to the data generating process gives an estimation of the negative Kullback-Leibler divergence between the statistical generative model and the true generative distribution. Using a set of canonical examples we show that this divergence provides a useful misspecification diagnostic, a model comparison tool, and a method to inform a generalised Bayesian update in the presence of misspecification for likelihood-based models. |
| Tasks | Bayesian Inference |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05810v1 |
| https://arxiv.org/pdf/1912.05810v1.pdf | |
| PWC | https://paperswithcode.com/paper/diagnosing-model-misspecification-and |
| Repo | |
| Framework | |
Genetic Deep Learning for Lung Cancer Screening
| Title | Genetic Deep Learning for Lung Cancer Screening |
| Authors | Hunter Park, Connor Monahan |
| Abstract | Convolutional neural networks (CNNs) have shown great promise in improving computer aided detection (CADe). From classifying tumors found via mammography as benign or malignant to automated detection of colorectal polyps in CT colonography, these advances have helped reduce the need for further evaluation with invasive testing and prevent errors from missed diagnoses by acting as a second observer in today’s fast paced and high volume clinical environment. CADe methods have become faster and more precise thanks to innovations in deep learning over the past several years. With advancements such as the inception module and utilization of residual connections, the approach to designing CNN architectures has become an art. It is customary to use proven models and fine tune them for particular tasks given a dataset, often requiring tedious work. We investigated using a genetic algorithm (GA) to conduct a neural architectural search (NAS) to generate a novel CNN architecture to find early stage lung cancer in chest x-rays (CXR). Using a dataset of over twelve thousand biopsy proven cases of lung cancer, the trained classification model achieved an accuracy of 97.15% with a PPV of 99.88% and a NPV of 94.81%, beating models such as Inception-V3 and ResNet-152 while simultaneously reducing the number of parameters a factor of 4 and 14, respectively. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11849v1 |
| https://arxiv.org/pdf/1907.11849v1.pdf | |
| PWC | https://paperswithcode.com/paper/genetic-deep-learning-for-lung-cancer |
| Repo | |
| Framework | |
Search Efficient Binary Network Embedding
| Title | Search Efficient Binary Network Embedding |
| Authors | Daokun Zhang, Jie Yin, Xingquan Zhu, Chengqi Zhang |
| Abstract | Traditional network embedding primarily focuses on learning a dense vector representation for each node, which encodes network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned dense vector representations are inefficient for large-scale similarity search, which requires to find the nearest neighbor measured by Euclidean distance in a continuous vector space. In this paper, we propose a search efficient binary network embedding algorithm called BinaryNE to learn a sparse binary code for each node, by simultaneously modeling node context relations and node attribute relations through a three-layer neural network. BinaryNE learns binary node representations efficiently through a stochastic gradient descent based online learning algorithm. The learned binary encoding not only reduces memory usage to represent each node, but also allows fast bit-wise comparisons to support much quicker network node search compared to Euclidean distance or other distance measures. Our experiments and comparisons show that BinaryNE not only delivers more than 23 times faster search speed, but also provides comparable or better search quality than traditional continuous vector based network embedding methods. |
| Tasks | Network Embedding |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04097v1 |
| http://arxiv.org/pdf/1901.04097v1.pdf | |
| PWC | https://paperswithcode.com/paper/search-efficient-binary-network-embedding |
| Repo | |
| Framework | |
TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces
| Title | TrIK-SVM : an alternative decomposition for kernel methods in Krein spaces |
| Authors | Gaëlle Loosli |
| Abstract | The proposed work aims at proposing a alternative kernel decomposition in the context of kernel machines with indefinite kernels. The original paper of KSVM (SVM in Kre\v{i}n spaces) uses the eigen-decomposition, our proposition avoids this decompostion. We explain how it can help in designing an algorithm that won’t require to compute the full kernel matrix. Finally we illustrate the good behavior of the proposed method compared to KSVM. |
| Tasks | |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10569v1 |
| http://arxiv.org/pdf/1902.10569v1.pdf | |
| PWC | https://paperswithcode.com/paper/trik-svm-an-alternative-decomposition-for |
| Repo | |
| Framework | |
