Paper Group ANR 1213
Efficient EM-Variational Inference for Hawkes Process. Expressive mechanisms for equitable rent division on a budget. Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability. What’s in the box? Explaining the black-box model through an evaluation of its interpretable features. Nucleus Neural Network: A Data-driven S …
Efficient EM-Variational Inference for Hawkes Process
| Title | Efficient EM-Variational Inference for Hawkes Process |
| Authors | Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen |
| Abstract | In classical Hawkes process, the baseline intensity and triggering kernel are assumed to be a constant and parametric function respectively, which limits the model flexibility. To generalize it, we present a fully Bayesian nonparametric model, namely Gaussian process modulated Hawkes process and propose an EM-variational inference scheme. In this model, a transformation of Gaussian process is used as a prior on the baseline intensity and triggering kernel. By introducing a latent branching structure, the inference of baseline intensity and triggering kernel is decoupled and the variational inference scheme is embedded into an EM framework naturally. We also provide a series of schemes to accelerate the inference. Results of synthetic and real data experiments show that the underlying baseline intensity and triggering kernel can be recovered without parametric restriction and our Bayesian nonparametric estimation is superior to other state of the arts. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12251v2 |
| https://arxiv.org/pdf/1905.12251v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-em-variational-inference-for-hawkes |
| Repo | |
| Framework | |
Expressive mechanisms for equitable rent division on a budget
| Title | Expressive mechanisms for equitable rent division on a budget |
| Authors | Rodrigo A. Velez |
| Abstract | We study the incentive properties of envy-free mechanisms for the allocation of rooms and payments of rent among financially constrained roommates. Each agent reports her values for rooms, her housing earmark (soft budget), and an index that reflects the difficulty the agent experiences from having to pay over this amount. Then an envy-free allocation for these reports is recommended. We identify conditions under which the complete information non-cooperative outcomes of these mechanisms are exactly the envy-free allocations with respect to true preferences. |
| Tasks | |
| Published | 2019-02-08 |
| URL | https://arxiv.org/abs/1902.02935v2 |
| https://arxiv.org/pdf/1902.02935v2.pdf | |
| PWC | https://paperswithcode.com/paper/expressive-mechanisms-for-equitable-rent |
| Repo | |
| Framework | |
Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability
| Title | Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability |
| Authors | Max Revay, Ian R. Manchester |
| Abstract | Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety. Methods that train stable recurrent neural networks, however, do so at a significant cost to expressibility. We propose an implicit model structure that allows for a convex parametrization of stable models using contraction analysis of non-linear systems. Using these stability conditions we propose a new approach to model initialization and then provide a number of empirical results comparing the performance of our proposed model set to previous stable RNNs and vanilla RNNs. By carefully controlling stability in the model, we observe a significant increase in the speed of training and model performance. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10402v1 |
| https://arxiv.org/pdf/1912.10402v1.pdf | |
| PWC | https://paperswithcode.com/paper/contracting-implicit-recurrent-neural |
| Repo | |
| Framework | |
What’s in the box? Explaining the black-box model through an evaluation of its interpretable features
| Title | What’s in the box? Explaining the black-box model through an evaluation of its interpretable features |
| Authors | Francesco Ventura, Tania Cerquitelli |
| Abstract | Algorithms are powerful and necessary tools behind a large part of the information we use every day. However, they may introduce new sources of bias, discrimination and other unfair practices that affect people who are unaware of it. Greater algorithm transparency is indispensable to provide more credible and reliable services. Moreover, requiring developers to design transparent algorithm-driven applications allows them to keep the model accessible and human understandable, increasing the trust of end users. In this paper we present EBAnO, a new engine able to produce prediction-local explanations for a black-box model exploiting interpretable feature perturbations. EBAnO exploits the hypercolumns representation together with the cluster analysis to identify a set of interpretable features of images. Furthermore two indices have been proposed to measure the influence of input features on the final prediction made by a CNN model. EBAnO has been preliminarily tested on a set of heterogeneous images. The results highlight the effectiveness of EBAnO in explaining the CNN classification through the evaluation of interpretable features influence. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1908.04348v1 |
| https://arxiv.org/pdf/1908.04348v1.pdf | |
| PWC | https://paperswithcode.com/paper/whats-in-the-box-explaining-the-black-box |
| Repo | |
| Framework | |
Nucleus Neural Network: A Data-driven Self-organized Architecture
| Title | Nucleus Neural Network: A Data-driven Self-organized Architecture |
| Authors | Jia Liu, Maoguo Gong, Haibo He |
| Abstract | Artificial neural networks which are inspired from the learning mechanism of brain have achieved great successes in many problems, especially those with deep layers. In this paper, we propose a nucleus neural network (NNN) and corresponding connecting architecture learning method. In a nucleus, there are no regular layers, i.e., a neuron may connect to all the neurons in the nucleus. This type of architecture gets rid of layer limitation and may lead to more powerful learning capability. It is crucial to determine the connections between them given numerous neurons. Based on the principle that more relevant input and output neuron pair deserves higher connecting density, we propose an efficient architecture learning model for the nucleus. Moreover, we improve the learning method for connecting weights and biases given the optimized architecture. We find that this novel architecture is robust to irrelevant components in test data. So we reconstruct a new dataset based on the MNIST dataset where the types of digital backgrounds in training and test sets are different. Experiments demonstrate that the proposed learner achieves significant improvement over traditional learners on the reconstructed data set. |
| Tasks | |
| Published | 2019-04-08 |
| URL | https://arxiv.org/abs/1904.04036v2 |
| https://arxiv.org/pdf/1904.04036v2.pdf | |
| PWC | https://paperswithcode.com/paper/nucleus-neural-network-for-super-robust |
| Repo | |
| Framework | |
Off-Policy Evaluation in Partially Observable Environments
| Title | Off-Policy Evaluation in Partially Observable Environments |
| Authors | Guy Tennenholtz, Shie Mannor, Uri Shalit |
| Abstract | This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Markov Decision Processes (POMDPs) and establish what we believe is the first off-policy evaluation result for POMDPs. In addition, we formulate a model in which observed and unobserved variables are decoupled into two dynamic processes, called a Decoupled POMDP. We show how off-policy evaluation can be performed under this new model, mitigating estimation errors inherent to general POMDPs. We demonstrate the pitfalls of off-policy evaluation in POMDPs using a well-known off-policy method, Importance Sampling, and compare it with our result on synthetic medical data. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03739v3 |
| https://arxiv.org/pdf/1909.03739v3.pdf | |
| PWC | https://paperswithcode.com/paper/off-policy-evaluation-in-partially-observable |
| Repo | |
| Framework | |
Optimality Implies Kernel Sum Classifiers are Statistically Efficient
| Title | Optimality Implies Kernel Sum Classifiers are Statistically Efficient |
| Authors | Raphael Arkady Meyer, Jean Honorio |
| Abstract | We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typical learning theoretic results which hold for all (potentially suboptimal) classifiers. Our work also justifies assumptions made in prior work on multiple kernel learning. As a byproduct of our analysis, we also provide a new form of Rademacher complexity for hypothesis classes containing only optimal classifiers. |
| Tasks | |
| Published | 2019-01-25 |
| URL | https://arxiv.org/abs/1901.09087v2 |
| https://arxiv.org/pdf/1901.09087v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-statistical-efficiency-of-optimal |
| Repo | |
| Framework | |
On geodesic triangles with right angles in a dually flat space
| Title | On geodesic triangles with right angles in a dually flat space |
| Authors | Frank Nielsen |
| Abstract | The dualistic structure of statistical manifolds in information geometry yields eight types of geodesic triangles passing through three given points, the triangle vertices. The interior angles of geodesic triangles can sum up to $\pi$ like in Euclidean/Mahalanobis flat geometry, or exhibit otherwise angle excesses or angle defects. In this paper, we initiate the study of geodesic triangles in dually flat spaces, termed Bregman manifolds, where a generalized Pythagorean theorem holds. We consider non-self dual Bregman manifolds since Mahalanobis self-dual manifolds amount to Euclidean geometry. First, we show how to construct geodesic triangles with either one, two, or three interior right angles, whenever it is possible. Second, we report a construction of triples of points for which the dual Pythagorean theorems hold simultaneously at a point, yielding two dual pairs of dual-type geodesics with right angles at that point. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03935v3 |
| https://arxiv.org/pdf/1910.03935v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-geodesic-triangles-with-right-angles-in-a |
| Repo | |
| Framework | |
A Bayesian Approach to Rule Mining
| Title | A Bayesian Approach to Rule Mining |
| Authors | Luis Ignacio Lopera González, Adrian Derungs, Oliver Amft |
| Abstract | In this paper, we introduce the increasing belief criterion in association rule mining. The criterion uses a recursive application of Bayes’ theorem to compute a rule’s belief. Extracted rules are required to have their belief increase with their last observation. We extend the taxonomy of association rule mining algorithms with a new branch for Bayesian rule mining~(BRM), which uses increasing belief as the rule selection criterion. In contrast, the well-established frequent association rule mining~(FRM) branch relies on the minimum-support concept to extract rules. We derive properties of the increasing belief criterion, such as the increasing belief boundary, no-prior-worries, and conjunctive premises. Subsequently, we implement a BRM algorithm using the increasing belief criterion, and illustrate its functionality in three experiments: (1)~a proof-of-concept to illustrate BRM properties, (2)~an analysis relating socioeconomic information and chemical exposure data, and (3)~mining behaviour routines in patients undergoing neurological rehabilitation. We illustrate how BRM is capable of extracting rare rules and does not suffer from support dilution. Furthermore, we show that BRM focuses on the individual event generating processes, while FRM focuses on their commonalities. We consider BRM’s increasing belief as an alternative criterion to thresholds on rule support, as often applied in FRM, to determine rule usefulness. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06432v2 |
| https://arxiv.org/pdf/1912.06432v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-approach-to-rule-mining |
| Repo | |
| Framework | |
Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction
| Title | Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction |
| Authors | Jue Wang, Ke Chen, Lidan Shou, Sai Wu, Sharad Mehrotra |
| Abstract | This paper addresses the problem of key phrase extraction from sentences. Existing state-of-the-art supervised methods require large amounts of annotated data to achieve good performance and generalization. Collecting labeled data is, however, often expensive. In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself. Briefly, given a sentence $s$ and an answer $a$, the model needs to choose the most appropriate question $\hat q$; meanwhile, for the given sentence $s$ and same question $\hat q$ selected in the previous step, the model will predict an answer $\hat a$. The model can support few-shot learning with very limited supervision. It can also be used to perform clustering analysis when no supervision is provided. Experimental results show that the proposed method outperforms typical supervised methods especially when given little labeled data. |
| Tasks | Few-Shot Learning |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.03898v1 |
| http://arxiv.org/pdf/1904.03898v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-few-shot-learning-for-dual |
| Repo | |
| Framework | |
The αμ Search Algorithm for the Game of Bridge
| Title | The αμ Search Algorithm for the Game of Bridge |
| Authors | Tristan Cazenave, Véronique Ventos |
| Abstract | {\alpha}{\mu} is an anytime heuristic search algorithm for incomplete information games that assumes perfect information for the opponents. {\alpha}{\mu} addresses the strategy fusion and non-locality problems encountered by Perfect Information Monte Carlo sampling. In this paper {\alpha}{\mu} is applied to the game of Bridge. |
| Tasks | |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07960v1 |
| https://arxiv.org/pdf/1911.07960v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-search-algorithm-for-the-game-of-bridge |
| Repo | |
| Framework | |
Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy
| Title | Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy |
| Authors | Jingxi Li, Deniz Mengu, Yi Luo, Yair Rivenson, Aydogan Ozcan |
| Abstract | Diffractive deep neural networks have been introduced earlier as an optical machine learning framework that uses task-specific diffractive surfaces designed by deep learning to all-optically perform inference, achieving promising performance for object classification and imaging. Here we demonstrate systematic improvements in diffractive optical neural networks based on a differential measurement technique that mitigates the non-negativity constraint of light intensity. In this scheme, each class is assigned to a separate pair of photodetectors, behind a diffractive network, and the class inference is made by maximizing the normalized signal difference between the detector pairs. Moreover, by utilizing the inherent parallelization capability of optical systems, we reduced the signal coupling between the positive and negative detectors of each class by dividing their optical path into two jointly-trained diffractive neural networks that work in parallel. We further made use of this parallelization approach, and divided individual classes among multiple jointly-trained differential diffractive neural networks. Using this class-specific differential detection in jointly-optimized diffractive networks, our simulations achieved testing accuracies of 98.52%, 91.48% and 50.82% for MNIST, Fashion-MNIST and grayscale CIFAR-10 datasets, respectively. Similar to ensemble methods practiced in machine learning, we also independently-optimized multiple differential diffractive networks that optically project their light onto a common detector plane, and achieved testing accuracies of 98.59%, 91.06% and 51.44% for MNIST, Fashion-MNIST and grayscale CIFAR-10, respectively. Through these systematic advances in designing diffractive neural networks, the reported classification accuracies set the state-of-the-art for an all-optical neural network design. |
| Tasks | Object Classification |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03417v2 |
| https://arxiv.org/pdf/1906.03417v2.pdf | |
| PWC | https://paperswithcode.com/paper/class-specific-differential-detection-in |
| Repo | |
| Framework | |
Predicting Future Pedestrian Motion in Video Sequences using Crowd Simulation
| Title | Predicting Future Pedestrian Motion in Video Sequences using Crowd Simulation |
| Authors | Cliceres dal Bianco, Soraia Raupp Musse |
| Abstract | While human and group analysis have become an important area in last decades, some current and relevant applications involve to estimate future motion of pedestrians in real video sequences. This paper presents a method to provide motion estimation of real pedestrians in next seconds, using crowd simulation. Our method is based on Physics and heuristics and use BioCrowds as crowd simulation methodology to estimate future positions of people in video sequences. Results show that our method for estimation works well even for complex videos where events can happen. The maximum achieved average error is $2.72$cm when estimating the future motion of 32 pedestrians with more than 2 seconds in advance. This paper discusses this and other results. |
| Tasks | Motion Estimation |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05448v1 |
| http://arxiv.org/pdf/1904.05448v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-future-pedestrian-motion-in-video |
| Repo | |
| Framework | |
Learning Dense Wide Baseline Stereo Matching for People
| Title | Learning Dense Wide Baseline Stereo Matching for People |
| Authors | Akin Caliskan, Armin Mustafa, Evren Imre, Adrian Hilton |
| Abstract | Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A synthetic people stereo patch dataset (S2P2) is introduced to learn wide baseline dense stereo matching for people. The proposed framework not only learns human specific features from synthetic data but also exploits pooling layer and data augmentation to adapt to real data. The network learns from the human specific stereo patches from the proposed dataset for wide-baseline stereo estimation. In addition to patch match learning, a stereo constraint is introduced in the framework to solve wide baseline stereo reconstruction of humans. Quantitative and qualitative performance evaluation against state-of-the-art methods of proposed method demonstrates improved wide baseline stereo reconstruction on challenging datasets. We show that it is possible to learn stereo matching from synthetic people dataset and improve performance on real datasets for stereo reconstruction of people from narrow and wide baseline stereo data. |
| Tasks | Data Augmentation, Stereo Matching |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01241v1 |
| https://arxiv.org/pdf/1910.01241v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-dense-wide-baseline-stereo-matching |
| Repo | |
| Framework | |
Brain Tumor Segmentation on MRI with Missing Modalities
| Title | Brain Tumor Segmentation on MRI with Missing Modalities |
| Authors | Yan Shen, Mingchen Gao |
| Abstract | Brain Tumor Segmentation from magnetic resonance imaging (MRI) is a critical technique for early diagnosis. However, rather than having complete four modalities as in BraTS dataset, it is common to have missing modalities in clinical scenarios. We design a brain tumor segmentation algorithm that is robust to the absence of any modality. Our network includes a channel-independent encoding path and a feature-fusion decoding path. We use self-supervised training through channel dropout and also propose a novel domain adaptation method on feature maps to recover the information from the missing channel. Our results demonstrate that the quality of the segmentation depends on which modality is missing. Furthermore, we also discuss and visualize the contribution of each modality to the segmentation results. Their contributions are along well with the expert screening routine. |
| Tasks | Brain Tumor Segmentation, Domain Adaptation |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07290v1 |
| http://arxiv.org/pdf/1904.07290v1.pdf | |
| PWC | https://paperswithcode.com/paper/brain-tumor-segmentation-on-mri-with-missing |
| Repo | |
| Framework | |
