Paper Group ANR 581
Multi-objective Bayesian optimisation with preferences over objectives. Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization. CameraNet: A Two-Stage Framework for Effective Camera ISP Learning. Adversarial Vulnerability Bounds for Gaussian Process Classification. Cross-Channel Correlation Pres …
Multi-objective Bayesian optimisation with preferences over objectives
| Title | Multi-objective Bayesian optimisation with preferences over objectives |
| Authors | Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta, Svetha Venkatesh |
| Abstract | We present a multi-objective Bayesian optimisation algorithm that allows the user to express preference-order constraints on the objectives of the type “objective A is more important than objective B”. These preferences are defined based on the stability of the obtained solutions with respect to preferred objective functions. Rather than attempting to find a representative subset of the complete Pareto front, our algorithm selects those Pareto-optimal points that satisfy these constraints. We formulate a new acquisition function based on expected improvement in dominated hypervolume (EHI) to ensure that the subset of Pareto front satisfying the constraints is thoroughly explored. The hypervolume calculation is weighted by the probability of a point satisfying the constraints from a gradient Gaussian Process model. We demonstrate our algorithm on both synthetic and real-world problems. |
| Tasks | Bayesian Optimisation |
| Published | 2019-02-12 |
| URL | https://arxiv.org/abs/1902.04228v3 |
| https://arxiv.org/pdf/1902.04228v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-bayesian-optimisation-with |
| Repo | |
| Framework | |
Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization
| Title | Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization |
| Authors | Takuya Shimada, Han Bao, Issei Sato, Masashi Sugiyama |
| Abstract | Pairwise similarities and dissimilarities between data points might be easier to obtain than fully labeled data in real-world classification problems, e.g., in privacy-aware situations. To handle such pairwise information, an empirical risk minimization approach has been proposed, giving an unbiased estimator of the classification risk that can be computed only from pairwise similarities and unlabeled data. However, this direction cannot handle pairwise dissimilarities so far. On the other hand, semi-supervised clustering is one of the methods which can use both similarities and dissimilarities. Nevertheless, they typically require strong geometrical assumptions on the data distribution such as the manifold assumption, which may deteriorate the performance. In this paper, we derive an unbiased risk estimator which can handle all of similarities/dissimilarities and unlabeled data. We theoretically establish estimation error bounds and experimentally demonstrate the practical usefulness of our empirical risk minimization method. |
| Tasks | |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11717v1 |
| http://arxiv.org/pdf/1904.11717v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-from-pairwise |
| Repo | |
| Framework | |
CameraNet: A Two-Stage Framework for Effective Camera ISP Learning
| Title | CameraNet: A Two-Stage Framework for Effective Camera ISP Learning |
| Authors | Zhetong Liang, Jianrui Cai, Zisheng Cao, Lei Zhang |
| Abstract | Traditional image signal processing (ISP) pipeline consists of a set of individual image processing components onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Due to the hand-crafted nature of the ISP components, traditional ISP pipeline has limited reconstruction quality under challenging scenes. Recently, the convolutional neural networks (CNNs) have demonstrated their competitiveness in solving many individual image processing problems, such as image denoising, demosaicking, white balance and contrast enhancement. However, it remains a question whether a CNN model can address the multiple tasks inside an ISP pipeline simultaneously. We make a good attempt along this line and propose a novel framework, which we call CameraNet, for effective and general ISP pipeline learning. The CameraNet is composed of two CNN modules to account for two sets of relatively uncorrelated subtasks in an ISP pipeline: restoration and enhancement. To train the two-stage CameraNet model, we specify two groundtruths that can be easily created in the common workflow of photography. CameraNet is trained to progressively address the restoration and the enhancement subtasks with its two modules. Experiments show that the proposed CameraNet achieves consistently compelling reconstruction quality on three benchmark datasets and outperforms traditional ISP pipelines. |
| Tasks | Demosaicking, Denoising, Image Denoising |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01481v2 |
| https://arxiv.org/pdf/1908.01481v2.pdf | |
| PWC | https://paperswithcode.com/paper/cameranet-a-two-stage-framework-for-effective |
| Repo | |
| Framework | |
Adversarial Vulnerability Bounds for Gaussian Process Classification
| Title | Adversarial Vulnerability Bounds for Gaussian Process Classification |
| Authors | Michael Thomas Smith, Kathrin Grosse, Michael Backes, Mauricio A Alvarez |
| Abstract | Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devise an adversarial bound (AB) for a Gaussian process classifier, that holds for the entire input domain, bounding the potential for any future adversarial method to cause such misclassification. This is a formal guarantee of robustness, not just an empirically derived result. We investigate how to configure the classifier to maximise the bound, including the use of a sparse approximation, leading to the method producing a practical, useful and provably robust classifier, which we test using a variety of datasets. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08864v1 |
| https://arxiv.org/pdf/1909.08864v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-vulnerability-bounds-for-gaussian |
| Repo | |
| Framework | |
Cross-Channel Correlation Preserved Three-Stream Lightweight CNNs for Demosaicking
| Title | Cross-Channel Correlation Preserved Three-Stream Lightweight CNNs for Demosaicking |
| Authors | Niu Yan, Jihong Ouyang |
| Abstract | Demosaicking is a procedure to reconstruct full RGB images from Color Filter Array (CFA) samples, none of which has all color components available. Recent deep Convolutional Neural Networks (CNN) based models have obtained state of the art accuracy on benchmark datasets. However, due to the sequential feature extraction manner of CNNs, deep demosaicking models may be over slow for daily use cameras. In this paper, we decouple deep sequential demosaicking to three-stream lightweight networks, which restore the green channel, the green-red difference plane and the green-blue difference plane respectively. This strategy allows independent offline training and parallel online estimation, whilst preserving the intrinsic cross-channel correlation of natural images. Moreover, this allows designing each stream according to the various restoration difficulty of each channel. As validated by extensive experiments, our method achieves top accuracy at fast speed. Source code will be released along with paper publication. |
| Tasks | Demosaicking |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09884v2 |
| https://arxiv.org/pdf/1906.09884v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-channel-correlation-preserved-three |
| Repo | |
| Framework | |
The Efficiency Threshold for the Offspring Population Size of the ($μ$, $λ$) EA
| Title | The Efficiency Threshold for the Offspring Population Size of the ($μ$, $λ$) EA |
| Authors | Denis Antipov, Benjamin Doerr, Quentin Yang |
| Abstract | Understanding when evolutionary algorithms are efficient or not, and how they efficiently solve problems, is one of the central research tasks in evolutionary computation. In this work, we make progress in understanding the interplay between parent and offspring population size of the $(\mu,\lambda)$ EA. Previous works, roughly speaking, indicate that for $\lambda \ge (1+\varepsilon) e \mu$, this EA easily optimizes the OneMax function, whereas an offspring population size $\lambda \le (1 -\varepsilon) e \mu$ leads to an exponential runtime. Motivated also by the observation that in the efficient regime the $(\mu,\lambda)$ EA loses its ability to escape local optima, we take a closer look into this phase transition. Among other results, we show that when $\mu \le n^{1/2 - c}$ for any constant $c > 0$, then for any $\lambda \le e \mu$ we have a super-polynomial runtime. However, if $\mu \ge n^{2/3 + c}$, then for any $\lambda \ge e \mu$, the runtime is polynomial. For the latter result we observe that the $(\mu,\lambda)$ EA profits from better individuals also because these, by creating slightly worse offspring, stabilize slightly sub-optimal sub-populations. While these first results close to the phase transition do not yet give a complete picture, they indicate that the boundary between efficient and super-polynomial is not just the line $\lambda = e \mu$, and that the reasons for efficiency or not are more complex than what was known so far. |
| Tasks | |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.06981v1 |
| http://arxiv.org/pdf/1904.06981v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-efficiency-threshold-for-the-offspring |
| Repo | |
| Framework | |
Non-asymptotic Results for Langevin Monte Carlo: Coordinate-wise and Black-box Sampling
| Title | Non-asymptotic Results for Langevin Monte Carlo: Coordinate-wise and Black-box Sampling |
| Authors | Lingqing Shen, Krishnakumar Balasubramanian, Saeed Ghadimi |
| Abstract | Discretization of continuous-time diffusion processes, using gradient and Hessian information, is a popular technique for sampling. For example, the Euler-Maruyama discretization of the Langevin diffusion process, called as Langevin Monte Carlo (LMC), is a canonical algorithm for sampling from strongly log-concave densities. In this work, we make several theoretical contributions to the literature on such sampling techniques. Specifically, we first provide a Randomized Coordinate-wise LMC algorithm suitable for large-scale sampling problems and provide a theoretical analysis. We next consider the case of zeroth-order or black-box sampling where one only obtains evaluates of the density. Based on Gaussian Stein’s identities we then estimate the gradient and Hessian information and leverage it in the context of black-box sampling. We then provide a theoretical analysis of gradient and Hessian based discretizations of Langevin and kinetic Langevin diffusion processes for sampling, quantifying the non-asymptotic accuracy. We also consider high-dimensional black-box sampling under the assumption that the density depends only on a small subset of the entire coordinates. We propose a variable selection technique based on zeroth-order gradient estimates and establish its theoretical guarantees. Our theoretical contributions extend the practical applicability of sampling algorithms to the large-scale, black-box and high-dimensional settings. |
| Tasks | |
| Published | 2019-02-04 |
| URL | http://arxiv.org/abs/1902.01373v3 |
| http://arxiv.org/pdf/1902.01373v3.pdf | |
| PWC | https://paperswithcode.com/paper/non-asymptotic-results-for-langevin-monte |
| Repo | |
| Framework | |
Learning Adaptive Regularization for Image Labeling Using Geometric Assignment
| Title | Learning Adaptive Regularization for Image Labeling Using Geometric Assignment |
| Authors | Ruben Hühnerbein, Fabrizio Savarino, Stefania Petra, Christoph Schnörr |
| Abstract | We study the inverse problem of model parameter learning for pixelwise image labeling, using the linear assignment flow and training data with ground truth. This is accomplished by a Riemannian gradient flow on the manifold of parameters that determine the regularization properties of the assignment flow. Using the symplectic partitioned Runge–Kutta method for numerical integration, it is shown that deriving the sensitivity conditions of the parameter learning problem and its discretization commute. A convenient property of our approach is that learning is based on exact inference. Carefully designed experiments demonstrate the performance of our approach, the expressiveness of the mathematical model as well as its limitations, from the viewpoint of statistical learning and optimal control. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09976v1 |
| https://arxiv.org/pdf/1910.09976v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-adaptive-regularization-for-image |
| Repo | |
| Framework | |
Querying Zero-streaming Cameras
| Title | Querying Zero-streaming Cameras |
| Authors | Mengwei Xu, Tiantu Xu, Yunxin Liu, Xuanzhe Liu, Gang Huang, Felix Xiaozhu Lin |
| Abstract | Low-cost cameras grow rapidly, producing colossal videos that enable powerful analytics but also stress network and compute resources. An unexploited opportunity is that most of the videos remain “cold” without ever being queried. For resource efficiency, we advocate for these cameras to be zero-streaming: they capture videos directly to their cheap local storage and only communicate with the cloud when analytics is requested. To this end, we present a system that spans the cloud and cameras. Our key ideas are twofold. When capturing video frames, a camera learns accurate knowledge on a sparse sample of frames, rather than learning inaccurate knowledge on all frames; in executing one query, a camera processes frames in multiple passes with multiple operators trained and picked by the cloud during the query, rather than one pass processing with operator(s) decided ahead of the query. On diverse queries over 15 videos and with typical wireless network bandwidth and low-cost camera hardware, our system prototype runs at more than 100x video realtime. It outperforms competitive alternative designs by at least 4x and up to two orders of magnitude. |
| Tasks | |
| Published | 2019-04-28 |
| URL | https://arxiv.org/abs/1904.12342v3 |
| https://arxiv.org/pdf/1904.12342v3.pdf | |
| PWC | https://paperswithcode.com/paper/supporting-video-queries-on-zero-streaming |
| Repo | |
| Framework | |
Evidential positive opinion influence measures for viral marketing
| Title | Evidential positive opinion influence measures for viral marketing |
| Authors | Siwar Jendoubi, Arnaud Martin |
| Abstract | The Viral Marketing is a relatively new form of marketing that exploits social networks to promote a brand, a product, etc. The idea behind it is to find a set of influencers on the network that can trigger a large cascade of propagation and adoptions. In this paper, we will introduce an evidential opinion-based influence maximization model for viral marketing. Besides, our approach tackles three opinions based scenarios for viral marketing in the real world. The first scenario concerns influencers who have a positive opinion about the product. The second scenario deals with influencers who have a positive opinion about the product and produce effects on users who also have a positive opinion. The third scenario involves influence users who have a positive opinion about the product and produce effects on the negative opinion of other users concerning the product in question. Next, we proposed six influence measures, two for each scenario. We also use an influence maximization model that the set of detected influencers for each scenario. Finally, we show the performance of the proposed model with each influence measure through some experiments conducted on a generated dataset and a real world dataset collected from Twitter. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05028v1 |
| https://arxiv.org/pdf/1907.05028v1.pdf | |
| PWC | https://paperswithcode.com/paper/evidential-positive-opinion-influence |
| Repo | |
| Framework | |
ConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification
| Title | ConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification |
| Authors | Kathan Kashiparekh, Jyoti Narwariya, Pankaj Malhotra, Lovekesh Vig, Gautam Shroff |
| Abstract | Training deep neural networks often requires careful hyper-parameter tuning and significant computational resources. In this paper, we propose ConvTimeNet (CTN): an off-the-shelf deep convolutional neural network (CNN) trained on diverse univariate time series classification (TSC) source tasks. Once trained, CTN can be easily adapted to new TSC target tasks via a small amount of fine-tuning using labeled instances from the target tasks. We note that the length of convolutional filters is a key aspect when building a pre-trained model that can generalize to time series of different lengths across datasets. To achieve this, we incorporate filters of multiple lengths in all convolutional layers of CTN to capture temporal features at multiple time scales. We consider all 65 datasets with time series of lengths up to 512 points from the UCR TSC Benchmark for training and testing transferability of CTN: We train CTN on a randomly chosen subset of 24 datasets using a multi-head approach with a different softmax layer for each training dataset, and study generalizability and transferability of the learned filters on the remaining 41 TSC datasets. We observe significant gains in classification accuracy as well as computational efficiency when using pre-trained CTN as a starting point for subsequent task-specific fine-tuning compared to existing state-of-the-art TSC approaches. We also provide qualitative insights into the working of CTN by: i) analyzing the activations and filters of first convolution layer suggesting the filters in CTN are generically useful, ii) analyzing the impact of the design decision to incorporate multiple length decisions, and iii) finding regions of time series that affect the final classification decision via occlusion sensitivity analysis. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-04-29 |
| URL | http://arxiv.org/abs/1904.12546v2 |
| http://arxiv.org/pdf/1904.12546v2.pdf | |
| PWC | https://paperswithcode.com/paper/convtimenet-a-pre-trained-deep-convolutional |
| Repo | |
| Framework | |
Origami Inspired Solar Panel Design
| Title | Origami Inspired Solar Panel Design |
| Authors | Chris Whitmire, Brij Rokad, Caleb Crumley |
| Abstract | The goal of this paper was to take a flat solar panel and make cuts on the panel to make smaller, but still viable solar panels. These smaller solar panels could then be arranged in a tree-like design. The hope was that by having solar panels faced in different directions in 3-dimensional space, the tree system would be able to pick up more sunlight than a flat solar panel. The results were promising, but this project did not take every factor into account. Specifically, optimum shape, temperature and the resistance of system, reflection of sun-rays were not explored in this project. This paper will take an approach from origami paper folding to create the optimum arrangement that will allow the overall system to absorb the maximum energy. Since the system stays stationary throughout the day, it can reduce the maintenance cost and excess energy use because it does not require solar tracking. In this project we have implemented a variety of Evolutionary Algorithms to find the most efficient way to cut a flat solar panel and arrange the resulting smaller panels. Each solution in the population will be tested by computing the amount of solar energy that is absorbed at particular times of the day. The EA will be exploring different combinations of angles and heights of the smaller panels on the tree such that the system can produce the maximum amount of power throughout the day. The performance of our Evolutionary algorithms are comparable to the performance of flat solar panels. Keywords: - Evolutionary Programming, Evolution Strategy, Genetic Algorithm, Solar Panel Optimization. |
| Tasks | |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06012v1 |
| https://arxiv.org/pdf/1905.06012v1.pdf | |
| PWC | https://paperswithcode.com/paper/origami-inspired-solar-panel-design |
| Repo | |
| Framework | |
RAPID: Early Classification of Explosive Transients using Deep Learning
| Title | RAPID: Early Classification of Explosive Transients using Deep Learning |
| Authors | Daniel Muthukrishna, Gautham Narayan, Kaisey S. Mandel, Rahul Biswas, Renée Hložek |
| Abstract | We present RAPID (Real-time Automated Photometric IDentification), a novel time-series classification tool capable of automatically identifying transients from within a day of the initial alert, to the full lifetime of a light curve. Using a deep recurrent neural network with Gated Recurrent Units (GRUs), we present the first method specifically designed to provide early classifications of astronomical time-series data, typing 12 different transient classes. Our classifier can process light curves with any phase coverage, and it does not rely on deriving computationally expensive features from the data, making RAPID well-suited for processing the millions of alerts that ongoing and upcoming wide-field surveys such as the Zwicky Transient Facility (ZTF), and the Large Synoptic Survey Telescope (LSST) will produce. The classification accuracy improves over the lifetime of the transient as more photometric data becomes available, and across the 12 transient classes, we obtain an average area under the receiver operating characteristic curve of 0.95 and 0.98 at early and late epochs, respectively. We demonstrate RAPID’s ability to effectively provide early classifications of observed transients from the ZTF data stream. We have made RAPID available as an open-source software package (https://astrorapid.readthedocs.io) for machine learning-based alert-brokers to use for the autonomous and quick classification of several thousand light curves within a few seconds. |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1904.00014v2 |
| https://arxiv.org/pdf/1904.00014v2.pdf | |
| PWC | https://paperswithcode.com/paper/rapid-early-classification-of-explosive |
| Repo | |
| Framework | |
Should we Reload Time Series Classification Performance Evaluation ? (a position paper)
| Title | Should we Reload Time Series Classification Performance Evaluation ? (a position paper) |
| Authors | Dominique Gay, Vincent Lemaire |
| Abstract | Since the introduction and the public availability of the \textsc{ucr} time series benchmark data sets, numerous Time Series Classification (TSC) methods has been designed, evaluated and compared to each others. We suggest a critical view of TSC performance evaluation protocols put in place in recent TSC literature. The main goal of this `position’ paper is to stimulate discussion and reflexion about performance evaluation in TSC literature. | |
| Tasks | Time Series, Time Series Classification |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.03300v1 |
| http://arxiv.org/pdf/1903.03300v1.pdf | |
| PWC | https://paperswithcode.com/paper/should-we-reload-time-series-classification |
| Repo | |
| Framework | |
Training Models to Extract Treatment Plans from Clinical Notes Using Contents of Sections with Headings
| Title | Training Models to Extract Treatment Plans from Clinical Notes Using Contents of Sections with Headings |
| Authors | Ananya Poddar, Bharath Dandala, Murthy Devarakonda |
| Abstract | Objective: Using natural language processing (NLP) to find sentences that state treatment plans in a clinical note, would automate plan extraction and would further enable their use in tools that help providers and care managers. However, as in the most NLP tasks on clinical text, creating gold standard to train and test NLP models is tedious and expensive. Fortuitously, sometimes but not always clinical notes contain sections with a heading that identifies the section as a plan. Leveraging contents of such labeled sections as a noisy training data, we assessed accuracy of NLP models trained with the data. Methods: We used common variations of plan headings and rule-based heuristics to find plan sections with headings in clinical notes, and we extracted sentences from them and formed a noisy training data of plan sentences. We trained Support Vector Machine (SVM) and Convolutional Neural Network (CNN) models with the data. We measured accuracy of the trained models on the noisy dataset using ten-fold cross validation and separately on a set-aside manually annotated dataset. Results: About 13% of 117,730 clinical notes contained treatment plans sections with recognizable headings in the 1001 longitudinal patient records that were obtained from Cleveland Clinic under an IRB approval. We were able to extract and create a noisy training data of 13,492 plan sentences from the clinical notes. CNN achieved best F measures, 0.91 and 0.97 in the cross-validation and set-aside evaluation experiments respectively. SVM slightly underperformed with F measures of 0.89 and 0.96 in the same experiments. Conclusion: Our study showed that the training supervised learning models using noisy plan sentences was effective in identifying them in all clinical notes. More broadly, sections with informal headings in clinical notes can be a good source for generating effective training data. |
| Tasks | |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11930v1 |
| https://arxiv.org/pdf/1906.11930v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-models-to-extract-treatment-plans |
| Repo | |
| Framework | |
